Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3779. Min Range: -8.3779
Max Act: 8.3154. Min Act: -0.1700
Data Index: 447344 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3779. Min Range: -8.3779
Max Act: 8.3779. Min Act: -0.1700
Data Index: 1762080 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3779. Min Range: -8.3779
Max Act: 8.2529. Min Act: -0.1700
Data Index: 446360 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3779. Min Range: -8.3779
Max Act: 8.1279. Min Act: -0.1700
Data Index: 2642475 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3779. Min Range: -8.3779
Max Act: 8.0654. Min Act: -0.1700
Data Index: 7065958 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.9404. Min Act: -0.1700
Data Index: 4533240 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.9404. Min Act: -0.1700
Data Index: 3056191 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.8779. Min Act: -0.1700
Data Index: 6799771 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.8779. Min Act: -0.1700
Data Index: 5671506 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.8779. Min Act: -0.1700
Data Index: 2325853 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.8154. Min Act: -0.1700
Data Index: 3233094 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.7529. Min Act: -0.1700
Data Index: 8195205 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.8154. Min Act: -0.1700
Data Index: 6918299 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.8154. Min Act: -0.1700
Data Index: 5272898 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.7529. Min Act: -0.1700
Data Index: 5549708 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.7529. Min Act: -0.1700
Data Index: 2194744 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.7529. Min Act: -0.1700
Data Index: 8121229 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.7529. Min Act: -0.1700
Data Index: 3092599 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.7529. Min Act: -0.1700
Data Index: 1267231 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3779. Min Range: -8.3779
Max Act: 7.7529. Min Act: -0.1700
Data Index: 6648240 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19