Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.8664. Min Act: -0.1700
Data Index: 2743907 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.8352. Min Act: -0.1700
Data Index: 8363837 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.8664. Min Act: -0.1700
Data Index: 2825462 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.8352. Min Act: -0.1700
Data Index: 6434509 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.8352. Min Act: -0.1700
Data Index: 6434498 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.7727. Min Act: -0.1700
Data Index: 1817880 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.7727. Min Act: -0.1700
Data Index: 279279 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.7102. Min Act: -0.1700
Data Index: 8363827 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.6164. Min Act: -0.1700
Data Index: 4748685 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.5539. Min Act: -0.1700
Data Index: 4819417 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.5227. Min Act: -0.1700
Data Index: 279278 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.4914. Min Act: -0.1700
Data Index: 3957488 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.4914. Min Act: -0.1700
Data Index: 279276 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.3352. Min Act: -0.1700
Data Index: 5266201 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.2414. Min Act: -0.1700
Data Index: 1817895 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.2414. Min Act: -0.1700
Data Index: 8217426 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.2102. Min Act: -0.1700
Data Index: 5726519 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.2102. Min Act: -0.1700
Data Index: 5592815 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.2102. Min Act: -0.1700
Data Index: 2447635 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8664. Min Range: -5.8664
Max Act: 5.2102. Min Act: -0.1700
Data Index: 5726510 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19