Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.9396. Min Act: -0.1700
Data Index: 4255935 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.6583. Min Act: -0.1700
Data Index: 2637315 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.6583. Min Act: -0.1700
Data Index: 6414621 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.6271. Min Act: -0.1700
Data Index: 8407954 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.6271. Min Act: -0.1700
Data Index: 359876 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.4708. Min Act: -0.1700
Data Index: 2005709 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.4083. Min Act: -0.1700
Data Index: 75371 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.3771. Min Act: -0.1700
Data Index: 1906418 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.3458. Min Act: -0.1700
Data Index: 4954933 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2833. Min Act: -0.1700
Data Index: 5038776 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.3146. Min Act: -0.1700
Data Index: 6295299 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2833. Min Act: -0.1700
Data Index: 4197723 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2833. Min Act: -0.1700
Data Index: 938013 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2521. Min Act: -0.1700
Data Index: 5035181 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2208. Min Act: -0.1700
Data Index: 2493088 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2208. Min Act: -0.1700
Data Index: 2692907 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2521. Min Act: -0.1700
Data Index: 2570623 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2208. Min Act: -0.1700
Data Index: 5119181 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.2208. Min Act: -0.1700
Data Index: 3015067 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9396. Min Range: -6.9396
Max Act: 6.1896. Min Act: -0.1700
Data Index: 1471505 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19