Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1594. Min Range: -9.1594
Max Act: 9.1594. Min Act: -0.1700
Data Index: 4800986 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1594. Min Range: -9.1594
Max Act: 9.1594. Min Act: -0.1700
Data Index: 3438122 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.9719. Min Act: -0.1700
Data Index: 3056491 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.9094. Min Act: -0.1700
Data Index: 5711161 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.7219. Min Act: -0.1700
Data Index: 851289 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.6594. Min Act: -0.1700
Data Index: 2001105 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.6594. Min Act: -0.1700
Data Index: 5908426 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.6594. Min Act: -0.1700
Data Index: 859008 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.6594. Min Act: -0.1700
Data Index: 3600901 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.5969. Min Act: -0.1700
Data Index: 8154983 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.5969. Min Act: -0.1700
Data Index: 728953 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.5344. Min Act: -0.1700
Data Index: 221358 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.5344. Min Act: -0.1700
Data Index: 5077812 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.5344. Min Act: -0.1700
Data Index: 7341094 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.5344. Min Act: -0.1700
Data Index: 7095324 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.5344. Min Act: -0.1700
Data Index: 6704699 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.4719. Min Act: -0.1700
Data Index: 1836588 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.4719. Min Act: -0.1700
Data Index: 3927624 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.4719. Min Act: -0.1700
Data Index: 8629418 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1594. Min Range: -9.1594
Max Act: 8.4719. Min Act: -0.1700
Data Index: 1702262 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19