Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3975 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0123. Min Range: -8.0123
Max Act: 8.0123. Min Act: -0.1700
Data Index: 1186855 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.7623. Min Act: -0.1700
Data Index: 1311776 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.7623. Min Act: -0.1700
Data Index: 1830450 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.6998. Min Act: -0.1700
Data Index: 5253770 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.5748. Min Act: -0.1700
Data Index: 1233127 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.5748. Min Act: -0.1700
Data Index: 5122548 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.5748. Min Act: -0.1700
Data Index: 264784 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.6373. Min Act: -0.1700
Data Index: 1747189 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.6373. Min Act: -0.1700
Data Index: 897344 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.5123. Min Act: -0.1700
Data Index: 6100795 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.5123. Min Act: -0.1700
Data Index: 3943067 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.5123. Min Act: -0.1700
Data Index: 1227230 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.5123. Min Act: -0.1700
Data Index: 1055816 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.4186. Min Act: -0.1700
Data Index: 6252768 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.4186. Min Act: -0.1700
Data Index: 4274286 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3873. Min Act: -0.1700
Data Index: 131720 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3873. Min Act: -0.1700
Data Index: 6499850 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3561. Min Act: -0.1700
Data Index: 1608360 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3873. Min Act: -0.1700
Data Index: 4928689 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0123. Min Range: -8.0123
Max Act: 7.3561. Min Act: -0.1700
Data Index: 2062471 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19