Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6186. Min Range: -8.6186
Max Act: 8.6186. Min Act: -0.1700
Data Index: 1112866 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6186. Min Range: -8.6186
Max Act: 8.2436. Min Act: -0.1700
Data Index: 5611948 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6186. Min Range: -8.6186
Max Act: 8.1811. Min Act: -0.1700
Data Index: 7930775 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.9311. Min Act: -0.1700
Data Index: 2359607 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.8061. Min Act: -0.1700
Data Index: 5912062 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.7436. Min Act: -0.1700
Data Index: 4549980 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.8061. Min Act: -0.1700
Data Index: 6003896 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.7436. Min Act: -0.1700
Data Index: 4808226 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.7436. Min Act: -0.1700
Data Index: 5987354 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.7436. Min Act: -0.1700
Data Index: 480875 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.7436. Min Act: -0.1700
Data Index: 1794856 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6811. Min Act: -0.1700
Data Index: 433041 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6811. Min Act: -0.1700
Data Index: 3588384 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6811. Min Act: -0.1700
Data Index: 291554 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6186. Min Act: -0.1700
Data Index: 5274712 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6186. Min Act: -0.1700
Data Index: 230593 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6186. Min Act: -0.1700
Data Index: 4282303 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6811. Min Act: -0.1700
Data Index: 1000169 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6186. Min Act: -0.1700
Data Index: 4187151 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6186. Min Range: -8.6186
Max Act: 7.6186. Min Act: -0.1700
Data Index: 3223901 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19