Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 985 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.6378. Min Act: -0.1700
Data Index: 7842640 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.5440. Min Act: -0.1700
Data Index: 8735323 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.4503. Min Act: -0.1700
Data Index: 7707260 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.4190. Min Act: -0.1700
Data Index: 2555529 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.3565. Min Act: -0.1700
Data Index: 3199951 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.3253. Min Act: -0.1700
Data Index: 3617268 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.3878. Min Act: -0.1700
Data Index: 3717904 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.3253. Min Act: -0.1700
Data Index: 5211556 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.2940. Min Act: -0.1700
Data Index: 6069372 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.2315. Min Act: -0.1700
Data Index: 389891 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.2315. Min Act: -0.1700
Data Index: 3177367 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.2315. Min Act: -0.1700
Data Index: 4420542 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.2003. Min Act: -0.1700
Data Index: 8521413 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.2003. Min Act: -0.1700
Data Index: 8323255 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.2003. Min Act: -0.1700
Data Index: 5236883 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.1690. Min Act: -0.1700
Data Index: 2959030 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.1690. Min Act: -0.1700
Data Index: 2115455 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.1690. Min Act: -0.1700
Data Index: 8250962 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.1690. Min Act: -0.1700
Data Index: 1424395 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6378. Min Range: -6.6378
Max Act: 6.1378. Min Act: -0.1700
Data Index: 1981393 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19