Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4492 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.1992. Min Act: -0.1700
Data Index: 1505790 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.1680. Min Act: -0.1700
Data Index: 2314049 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.0742. Min Act: -0.1700
Data Index: 1470689 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.0430. Min Act: -0.1700
Data Index: 8248962 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.0430. Min Act: -0.1700
Data Index: 1631818 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.0430. Min Act: -0.1700
Data Index: 4575342 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1992. Min Range: -7.1992
Max Act: 7.0430. Min Act: -0.1700
Data Index: 6054773 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.9805. Min Act: -0.1700
Data Index: 8029741 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.9492. Min Act: -0.1700
Data Index: 2902717 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.9180. Min Act: -0.1700
Data Index: 7502925 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.9180. Min Act: -0.1700
Data Index: 1663627 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.9180. Min Act: -0.1700
Data Index: 1174948 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.8867. Min Act: -0.1700
Data Index: 56331 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.8555. Min Act: -0.1700
Data Index: 8322115 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.8242. Min Act: -0.1700
Data Index: 4464188 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.7930. Min Act: -0.1700
Data Index: 4233237 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.7617. Min Act: -0.1700
Data Index: 8552929 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.7617. Min Act: -0.1700
Data Index: 4715253 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.7305. Min Act: -0.1700
Data Index: 8758555 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1992. Min Range: -7.1992
Max Act: 6.6992. Min Act: -0.1700
Data Index: 5988122 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19