Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 691 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.7363. Min Act: -0.1700
Data Index: 224084 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.7104. Min Act: -0.1700
Data Index: 3005407 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.7104. Min Act: -0.1700
Data Index: 4804572 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.7104. Min Act: -0.1700
Data Index: 3214858 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6757. Min Act: -0.1699
Data Index: 6407362 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6757. Min Act: -0.1700
Data Index: 2862139 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6843. Min Act: -0.1700
Data Index: 8535967 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6670. Min Act: -0.1700
Data Index: 5188647 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6496. Min Act: -0.1700
Data Index: 4288031 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6496. Min Act: -0.1700
Data Index: 5236870 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6409. Min Act: -0.1700
Data Index: 8535968 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6409. Min Act: -0.1700
Data Index: 4024886 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6409. Min Act: -0.1700
Data Index: 7748514 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6409. Min Act: -0.1700
Data Index: 2148272 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6496. Min Act: -0.1700
Data Index: 6466274 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6409. Min Act: -0.1700
Data Index: 4203055 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6234. Min Act: -0.1700
Data Index: 4826364 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6409. Min Act: -0.1700
Data Index: 6326682 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6234. Min Act: -0.1700
Data Index: 29447 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7363. Min Range: -1.7363
Max Act: 1.6234. Min Act: -0.1700
Data Index: 5432917 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19