Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4034 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4239. Min Range: -6.4239
Max Act: 6.4239. Min Act: -0.1700
Data Index: 1666232 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4239. Min Range: -6.4239
Max Act: 6.2364. Min Act: -0.1700
Data Index: 2157904 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4239. Min Range: -6.4239
Max Act: 6.1739. Min Act: -0.1700
Data Index: 1677294 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.9864. Min Act: -0.1700
Data Index: 1736865 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.9864. Min Act: -0.1700
Data Index: 97763 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.9864. Min Act: -0.1700
Data Index: 1701387 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.8926. Min Act: -0.1700
Data Index: 4731623 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.9239. Min Act: -0.1700
Data Index: 4480167 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.8926. Min Act: -0.1700
Data Index: 7503486 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.8614. Min Act: -0.1700
Data Index: 4592336 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.8301. Min Act: -0.1700
Data Index: 816648 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.8301. Min Act: -0.1700
Data Index: 1763318 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.7989. Min Act: -0.1700
Data Index: 5558886 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.7989. Min Act: -0.1700
Data Index: 490408 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.7676. Min Act: -0.1700
Data Index: 7479320 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.7676. Min Act: -0.1700
Data Index: 4351230 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.7676. Min Act: -0.1700
Data Index: 3855964 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.7676. Min Act: -0.1700
Data Index: 2884679 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 3574503 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4239. Min Range: -6.4239
Max Act: 5.7364. Min Act: -0.1700
Data Index: 4864819 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19