Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 40 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3055. Min Range: -6.3055
Max Act: 6.3055. Min Act: -0.1700
Data Index: 8193812 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.9617. Min Act: -0.1700
Data Index: 7402174 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.9617. Min Act: -0.1700
Data Index: 804838 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.8992. Min Act: -0.1700
Data Index: 3732334 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.8992. Min Act: -0.1700
Data Index: 4935744 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.8992. Min Act: -0.1700
Data Index: 5202631 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.8367. Min Act: -0.1700
Data Index: 6721228 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7430. Min Act: -0.1700
Data Index: 1692101 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7430. Min Act: -0.1700
Data Index: 207487 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7430. Min Act: -0.1700
Data Index: 3587600 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7430. Min Act: -0.1700
Data Index: 7720336 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7430. Min Act: -0.1700
Data Index: 5290044 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7430. Min Act: -0.1700
Data Index: 7018631 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7117. Min Act: -0.1700
Data Index: 6093251 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7117. Min Act: -0.1700
Data Index: 921328 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7117. Min Act: -0.1700
Data Index: 4934629 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7117. Min Act: -0.1700
Data Index: 520577 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7117. Min Act: -0.1700
Data Index: 4928553 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.6805. Min Act: -0.1700
Data Index: 7642852 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3055. Min Range: -6.3055
Max Act: 5.7117. Min Act: -0.1700
Data Index: 4925716 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19