Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4323. Min Range: -8.4323
Max Act: 8.4323. Min Act: -0.1700
Data Index: 1061346 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4323. Min Range: -8.4323
Max Act: 8.1823. Min Act: -0.1700
Data Index: 3506772 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4323. Min Range: -8.4323
Max Act: 8.1823. Min Act: -0.1700
Data Index: 3313224 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.9948. Min Act: -0.1700
Data Index: 1242135 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.9948. Min Act: -0.1700
Data Index: 6623495 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.9323. Min Act: -0.1700
Data Index: 1286338 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.9948. Min Act: -0.1700
Data Index: 6312464 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.8698. Min Act: -0.1700
Data Index: 6027985 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.8073. Min Act: -0.1700
Data Index: 1455813 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.8073. Min Act: -0.1700
Data Index: 917197 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.8073. Min Act: -0.1700
Data Index: 3626926 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.7448. Min Act: -0.1700
Data Index: 4729627 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.7136. Min Act: -0.1700
Data Index: 1748714 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.6823. Min Act: -0.1700
Data Index: 6686297 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.6823. Min Act: -0.1700
Data Index: 3863813 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.6823. Min Act: -0.1700
Data Index: 7694693 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.6198. Min Act: -0.1700
Data Index: 725949 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.6198. Min Act: -0.1700
Data Index: 554544 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.6198. Min Act: -0.1700
Data Index: 1038064 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4323. Min Range: -8.4323
Max Act: 7.6511. Min Act: -0.1700
Data Index: 301955 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19