Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.4589. Min Act: -0.1700
Data Index: 6251685 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 7882470 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 1401121 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3339. Min Act: -0.1700
Data Index: 7449586 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 7191599 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 150487 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 6703889 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 6345002 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 6081367 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 5843363 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 5483503 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 5218479 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 4616815 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 646825 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 3589644 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3339. Min Act: -0.1700
Data Index: 3249681 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 3196761 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3964. Min Act: -0.1700
Data Index: 2994304 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3339. Min Act: -0.1700
Data Index: 2163189 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4589. Min Range: -10.4589
Max Act: 10.3339. Min Act: -0.1700
Data Index: 2114197 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19