Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 870 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.6851. Min Act: -0.1700
Data Index: 504247 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.6539. Min Act: -0.1700
Data Index: 8435052 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.4976. Min Act: -0.1700
Data Index: 6054902 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.5289. Min Act: -0.1700
Data Index: 7641665 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.5289. Min Act: -0.1700
Data Index: 5733995 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.4976. Min Act: -0.1700
Data Index: 5833463 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.4351. Min Act: -0.1700
Data Index: 3168248 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.4351. Min Act: -0.1700
Data Index: 2516662 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.4351. Min Act: -0.1700
Data Index: 4004377 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.4039. Min Act: -0.1700
Data Index: 6764566 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3726. Min Act: -0.1700
Data Index: 3912107 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3414. Min Act: -0.1700
Data Index: 8118220 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3414. Min Act: -0.1700
Data Index: 7909268 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3726. Min Act: -0.1700
Data Index: 2243632 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3414. Min Act: -0.1700
Data Index: 6017317 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3101. Min Act: -0.1700
Data Index: 258183 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3101. Min Act: -0.1700
Data Index: 2706658 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3101. Min Act: -0.1700
Data Index: 3576959 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3101. Min Act: -0.1700
Data Index: 5152633 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6851. Min Range: -6.6851
Max Act: 6.3101. Min Act: -0.1700
Data Index: 8571866 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19