The human brain has long inspired the pursuit of artificial intelligence (AI). Recently, neuroimaging studies provide compelling evidence of alignment between the computational representation of artificial neural networks (ANNs) and the neural responses of the human brain to stimuli, suggesting that ANNs may employ brain-like information processing strategies. While such alignment has been observed across sensory modalities--visual, auditory, and linguistic--much of the focus has been on the behaviors of artificial neurons (ANs) at the population level, leaving the functional organization of individual ANs that facilitates such brain-like processes largely unexplored. In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs), the foundational organizational structure of the human brain. Specifically, we extract representative patterns from temporal responses of ANs in large language models (LLMs), and use them as fixed regressors to construct voxel-wise encoding models to predict brain activity recorded by functional magnetic resonance imaging (fMRI). This framework links the AN sub-groups to FBNs, enabling the delineation of brain-like functional organization within LLMs. Our findings reveal that LLMs (BERT and Llama 1-3) exhibit brain-like functional architecture, with sub-groups of artificial neurons mirroring the organizational patterns of well-established FBNs. Notably, the brain-like functional organization of LLMs evolves with the increased sophistication and capability, achieving an improved balance between the diversity of computational behaviors and the consistency of functional specializations. This research represents the first exploration of brain-like functional organization within LLMs, offering novel insights to inform the development of artificial general intelligence (AGI) with human brain principles.

翻译：长期以来，人类大脑一直启发着人工智能（AI）的研究。最近的神经影像学研究提供了有力证据，表明人工神经网络（ANNs）的计算表征与人类大脑对刺激的神经反应之间存在一致性，这暗示ANNs可能采用了类脑的信息处理策略。尽管这种一致性已在多种感觉模态（视觉、听觉和语言）中被观察到，但大部分研究关注的是人工神经元（ANs）在群体层面的行为，而对促成此类脑式过程的单个ANs的功能组织却鲜有探索。在本研究中，我们通过将人工神经元子群与功能脑网络（FBNs）——人脑的基础组织结构——直接耦合，来弥合这一差距。具体而言，我们从大型语言模型（LLMs）中ANs的时间响应中提取代表性模式，并将其作为固定回归因子来构建体素级编码模型，以预测功能磁共振成像（fMRI）记录的大脑活动。该框架将AN子群与FBNs联系起来，从而能够在LLMs内部描绘出类脑的功能组织。我们的研究结果表明，LLMs（BERT和Llama 1-3）展现出类脑的功能架构，其中人工神经元子群反映了成熟FBNs的组织模式。值得注意的是，LLMs的类脑功能组织随着模型复杂性和能力的提升而演化，在计算行为的多样性与功能特化的一致性之间达到了更好的平衡。这项研究首次探索了LLMs内部的类脑功能组织，为借鉴人脑原理开发通用人工智能（AGI）提供了新的见解。