Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1863 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3979. Min Range: -7.3979
Max Act: 7.3979. Min Act: -0.1700
Data Index: 4087679 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.8042. Min Act: -0.1700
Data Index: 8064850 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.7417. Min Act: -0.1700
Data Index: 4260031 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.7104. Min Act: -0.1700
Data Index: 4556279 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.7104. Min Act: -0.1700
Data Index: 1297726 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.6792. Min Act: -0.1700
Data Index: 2881372 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.6479. Min Act: -0.1700
Data Index: 4225970 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.5854. Min Act: -0.1700
Data Index: 2836426 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.6167. Min Act: -0.1700
Data Index: 3260567 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.5542. Min Act: -0.1700
Data Index: 2037422 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.5229. Min Act: -0.1700
Data Index: 4727907 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.4917. Min Act: -0.1700
Data Index: 5996385 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.5229. Min Act: -0.1700
Data Index: 424522 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.4604. Min Act: -0.1700
Data Index: 3308871 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.4292. Min Act: -0.1700
Data Index: 5393437 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.4604. Min Act: -0.1700
Data Index: 862495 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.4292. Min Act: -0.1700
Data Index: 5416936 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.3979. Min Act: -0.1700
Data Index: 6622898 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.3979. Min Act: -0.1700
Data Index: 8465847 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3979. Min Range: -7.3979
Max Act: 6.3667. Min Act: -0.1700
Data Index: 4835936 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19