Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.7242. Min Act: -0.1700
Data Index: 2012653 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.6617. Min Act: -0.1700
Data Index: 7166037 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.3179. Min Act: -0.1700
Data Index: 8296400 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.2554. Min Act: -0.1700
Data Index: 146748 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.1929. Min Act: -0.1700
Data Index: 6999650 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.1929. Min Act: -0.1700
Data Index: 5257313 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.1617. Min Act: -0.1700
Data Index: 5998499 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.1617. Min Act: -0.1700
Data Index: 3260400 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.0992. Min Act: -0.1700
Data Index: 2682530 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.0992. Min Act: -0.1700
Data Index: 541374 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.0679. Min Act: -0.1700
Data Index: 2601181 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.0679. Min Act: -0.1700
Data Index: 5950865 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.0367. Min Act: -0.1700
Data Index: 7362988 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.0054. Min Act: -0.1700
Data Index: 4151174 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7242. Min Range: -5.7242
Max Act: 5.0367. Min Act: -0.1700
Data Index: 7090439 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7242. Min Range: -5.7242
Max Act: 4.9742. Min Act: -0.1700
Data Index: 7603991 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7242. Min Range: -5.7242
Max Act: 4.9742. Min Act: -0.1700
Data Index: 6923188 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7242. Min Range: -5.7242
Max Act: 4.9742. Min Act: -0.1700
Data Index: 8206110 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7242. Min Range: -5.7242
Max Act: 4.9742. Min Act: -0.1700
Data Index: 639004 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7242. Min Range: -5.7242
Max Act: 4.9742. Min Act: -0.1700
Data Index: 5649576 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19