Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1988 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1857. Min Range: -4.1857
Max Act: 4.1857. Min Act: -0.1700
Data Index: 7318914 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.9669. Min Act: -0.1700
Data Index: 371521 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.9356. Min Act: -0.1700
Data Index: 1459317 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.9356. Min Act: -0.1700
Data Index: 4181071 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.9356. Min Act: -0.1700
Data Index: 6311340 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.8731. Min Act: -0.1700
Data Index: 5224425 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.8731. Min Act: -0.1700
Data Index: 1778857 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.8731. Min Act: -0.1700
Data Index: 1958967 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.8418. Min Act: -0.1700
Data Index: 8326465 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.8418. Min Act: -0.1700
Data Index: 5964925 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.8105. Min Act: -0.1700
Data Index: 4310903 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.8105. Min Act: -0.1700
Data Index: 650209 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.8105. Min Act: -0.1700
Data Index: 4839205 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.7793. Min Act: -0.1700
Data Index: 678184 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.7793. Min Act: -0.1700
Data Index: 6143601 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.7323. Min Act: -0.1700
Data Index: 3694352 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.7167. Min Act: -0.1700
Data Index: 953282 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.7011. Min Act: -0.1700
Data Index: 4470713 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.7011. Min Act: -0.1700
Data Index: 6349876 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1857. Min Range: -4.1857
Max Act: 3.7011. Min Act: -0.1700
Data Index: 1990300 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19