Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5775 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.6040. Min Act: -0.1700
Data Index: 2227610 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.5103. Min Act: -0.1700
Data Index: 810066 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.4165. Min Act: -0.1700
Data Index: 1316645 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.4165. Min Act: -0.1700
Data Index: 2800630 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.3853. Min Act: -0.1700
Data Index: 7891382 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.3853. Min Act: -0.1700
Data Index: 2781897 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.3540. Min Act: -0.1700
Data Index: 5877598 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.3228. Min Act: -0.1700
Data Index: 7951262 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.2603. Min Act: -0.1700
Data Index: 2807421 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.2603. Min Act: -0.1700
Data Index: 1189404 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.2290. Min Act: -0.1700
Data Index: 8335647 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.1977. Min Act: -0.1700
Data Index: 3980637 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.1040. Min Act: -0.1700
Data Index: 8413720 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.1352. Min Act: -0.1700
Data Index: 6621014 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.1352. Min Act: -0.1700
Data Index: 4950071 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.1040. Min Act: -0.1700
Data Index: 8440174 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.1040. Min Act: -0.1700
Data Index: 1973161 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.0727. Min Act: -0.1700
Data Index: 4432693 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.1040. Min Act: -0.1700
Data Index: 1272317 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6040. Min Range: -4.6040
Max Act: 4.0727. Min Act: -0.1700
Data Index: 4445046 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19