Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4752 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1169. Min Range: -6.1169
Max Act: 6.1169. Min Act: -0.1700
Data Index: 1755547 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.9294. Min Act: -0.1700
Data Index: 4325362 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.9294. Min Act: -0.1700
Data Index: 3800007 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.8044. Min Act: -0.1700
Data Index: 6925020 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.6794. Min Act: -0.1700
Data Index: 5190924 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.6794. Min Act: -0.1700
Data Index: 1811432 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.6482. Min Act: -0.1700
Data Index: 1821536 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.6482. Min Act: -0.1700
Data Index: 3862028 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.6482. Min Act: -0.1700
Data Index: 8821103 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.6169. Min Act: -0.1700
Data Index: 3677020 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.6169. Min Act: -0.1700
Data Index: 5998671 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.6169. Min Act: -0.1700
Data Index: 3187045 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.5857. Min Act: -0.1700
Data Index: 3234596 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.5857. Min Act: -0.1700
Data Index: 752725 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.5857. Min Act: -0.1700
Data Index: 6991971 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.5544. Min Act: -0.1700
Data Index: 7756206 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.5857. Min Act: -0.1700
Data Index: 1821535 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.5544. Min Act: -0.1700
Data Index: 1729113 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.5544. Min Act: -0.1700
Data Index: 2606097 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1169. Min Range: -6.1169
Max Act: 5.5232. Min Act: -0.1700
Data Index: 342360 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19