The Importance of Prompt Tuning for Automated Neuron Explanations

November 2023
NeurIPS 2023 Workshop ATTRIB, Accepted
Justin Lee, Tuomas Oikarinen, Arjun Chatha, Keng-Chi Chang, Yilan Chen, Tsui-Wei (Lily) Weng

Recent advances have greatly increased the capabilities of large language models (LLMs), but our understanding of the models and their safety has not progressed as fast. In this paper we aim to understand LLMs deeper by studying their individual neurons. We build upon previous work showing large language models such as GPT-4 can be useful in explaining what each neuron in a language model does. Specifically, we analyze the effect of the prompt used to generate explanations and show that reformatting the explanation prompt in a more natural way can significantly improve neuron explanation quality and greatly reduce computational cost. We demonstrate the effects of our new prompts in three different ways, incorporating both automated and human evaluations.

  • Study neuron-level explanability by prompting LLMs with activated patterns.
  • Evaluate different prompting methods with both machine & humans.