Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4474 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5176. Min Range: -6.5176
Max Act: 6.5176. Min Act: -0.1700
Data Index: 7168958 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5176. Min Range: -6.5176
Max Act: 6.3613. Min Act: -0.1700
Data Index: 7437178 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5176. Min Range: -6.5176
Max Act: 6.2363. Min Act: -0.1700
Data Index: 3803694 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5176. Min Range: -6.5176
Max Act: 6.2051. Min Act: -0.1700
Data Index: 4682443 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5176. Min Range: -6.5176
Max Act: 6.1738. Min Act: -0.1700
Data Index: 5705627 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5176. Min Range: -6.5176
Max Act: 6.1113. Min Act: -0.1700
Data Index: 6193108 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5176. Min Range: -6.5176
Max Act: 6.0488. Min Act: -0.1700
Data Index: 4727677 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5176. Min Range: -6.5176
Max Act: 6.0176. Min Act: -0.1700
Data Index: 6072417 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.9863. Min Act: -0.1700
Data Index: 5741799 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.9238. Min Act: -0.1700
Data Index: 8772255 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.9551. Min Act: -0.1700
Data Index: 2783658 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.9863. Min Act: -0.1700
Data Index: 7514935 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.9238. Min Act: -0.1700
Data Index: 5615352 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.9238. Min Act: -0.1700
Data Index: 6020076 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.8926. Min Act: -0.1700
Data Index: 1575843 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.9238. Min Act: -0.1700
Data Index: 139260 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.9238. Min Act: -0.1700
Data Index: 201925 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.8926. Min Act: -0.1700
Data Index: 5795308 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.8926. Min Act: -0.1700
Data Index: 6458592 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5176. Min Range: -6.5176
Max Act: 5.8613. Min Act: -0.1700
Data Index: 5898344 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19