Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3650 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.9993. Min Act: -0.1700
Data Index: 7264438 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.9368. Min Act: -0.1700
Data Index: 4269799 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.7805. Min Act: -0.1700
Data Index: 2189440 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.7180. Min Act: -0.1700
Data Index: 477855 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.6868. Min Act: -0.1700
Data Index: 4447212 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.6868. Min Act: -0.1700
Data Index: 3925010 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.6555. Min Act: -0.1700
Data Index: 520439 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.5930. Min Act: -0.1700
Data Index: 4141165 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.5930. Min Act: -0.1700
Data Index: 7752711 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.5930. Min Act: -0.1700
Data Index: 6731759 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.5930. Min Act: -0.1700
Data Index: 41958 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.5618. Min Act: -0.1700
Data Index: 2423760 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.5618. Min Act: -0.1700
Data Index: 358478 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.4993. Min Act: -0.1700
Data Index: 6838279 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.4680. Min Act: -0.1700
Data Index: 1089904 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.4993. Min Act: -0.1700
Data Index: 5006872 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.4993. Min Act: -0.1700
Data Index: 7164666 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.4993. Min Act: -0.1700
Data Index: 434402 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.4680. Min Act: -0.1700
Data Index: 6059280 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9993. Min Range: -7.9993
Max Act: 7.4680. Min Act: -0.1700
Data Index: 1449724 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19