We observe an empirical phenomenon in Large Language Models (LLMs) -- very few activations exhibit significantly larger values than others (e.g., 100,000 times larger). We call them massive activations. First, we demonstrate the widespread existence of massive activations across various LLMs and characterize their locations. Second, we find their values largely stay constant regardless of the input, and they function as indispensable bias terms in LLMs. Third, these massive activations lead to the concentration of attention probabilities to their corresponding tokens, and further, implicit bias terms in the self-attention output. Last, we also study massive activations in Vision Transformers.

翻译：我们在大型语言模型（LLMs）中观察到一个经验现象——极少数激活值显著大于其他激活值（例如，相差10万倍）。我们将其称为大规模激活。首先，我们证明了大规模激活在不同LLMs中普遍存在，并刻画了其位置特征。其次，我们发现这些值在很大程度上不随输入变化而变化，并在LLMs中起到不可或缺的偏置项作用。第三，这些大规模激活导致注意力概率集中于对应词元，并进一步在自注意力输出中形成隐式偏置项。最后，我们还研究了视觉Transformer中的大规模激活现象。