Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0729. Min Range: -8.0729
Max Act: 8.0729. Min Act: -0.1700
Data Index: 523977 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.7604. Min Act: -0.1700
Data Index: 4816302 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.6979. Min Act: -0.1700
Data Index: 8223515 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.6979. Min Act: -0.1700
Data Index: 3471161 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.6354. Min Act: -0.1700
Data Index: 5497998 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.6354. Min Act: -0.1700
Data Index: 6756354 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.6354. Min Act: -0.1700
Data Index: 7961329 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.5104. Min Act: -0.1700
Data Index: 1899347 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.5104. Min Act: -0.1700
Data Index: 7354989 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.5104. Min Act: -0.1700
Data Index: 2134293 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.5104. Min Act: -0.1700
Data Index: 1705864 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.5104. Min Act: -0.1700
Data Index: 5505838 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.4791. Min Act: -0.1700
Data Index: 5348144 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.4791. Min Act: -0.1700
Data Index: 5115504 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.4791. Min Act: -0.1700
Data Index: 8550233 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.4479. Min Act: -0.1700
Data Index: 8294530 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.4479. Min Act: -0.1700
Data Index: 6345571 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.4791. Min Act: -0.1700
Data Index: 8062570 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.4166. Min Act: -0.1700
Data Index: 3107151 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0729. Min Range: -8.0729
Max Act: 7.4166. Min Act: -0.1700
Data Index: 7683869 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19