Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 232 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.8124. Min Act: -0.1700
Data Index: 2206724 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7499. Min Act: -0.1700
Data Index: 4188155 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7812. Min Act: -0.1700
Data Index: 2701894 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7499. Min Act: -0.1700
Data Index: 7059010 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7499. Min Act: -0.1700
Data Index: 1008807 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7030. Min Act: -0.1700
Data Index: 7165316 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7186. Min Act: -0.1700
Data Index: 6816711 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7342. Min Act: -0.1700
Data Index: 5155125 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7186. Min Act: -0.1700
Data Index: 5056713 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7030. Min Act: -0.1700
Data Index: 6646302 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.7186. Min Act: -0.1700
Data Index: 4098915 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6873. Min Act: -0.1700
Data Index: 3881891 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6560. Min Act: -0.1700
Data Index: 2668195 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6873. Min Act: -0.1700
Data Index: 37372 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6404. Min Act: -0.1700
Data Index: 1784516 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6560. Min Act: -0.1700
Data Index: 7504158 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6717. Min Act: -0.1700
Data Index: 1660886 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6247. Min Act: -0.1700
Data Index: 5663143 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6404. Min Act: -0.1700
Data Index: 4827510 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8124. Min Range: -3.8124
Max Act: 3.6404. Min Act: -0.1700
Data Index: 5787096 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19