Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.6395. Min Act: -0.1700
Data Index: 5032204 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.6707. Min Act: -0.1700
Data Index: 1321052 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.5457. Min Act: -0.1700
Data Index: 4325166 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.5145. Min Act: -0.1700
Data Index: 2052561 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.4520. Min Act: -0.1700
Data Index: 7727882 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.4520. Min Act: -0.1700
Data Index: 7451034 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.3895. Min Act: -0.1700
Data Index: 7884002 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.3895. Min Act: -0.1700
Data Index: 7884001 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.3582. Min Act: -0.1700
Data Index: 5752823 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.3582. Min Act: -0.1700
Data Index: 6969417 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 2644772 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 6672393 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 3824323 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 6757404 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.2020. Min Act: -0.1700
Data Index: 4244717 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 3937211 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.2020. Min Act: -0.1700
Data Index: 5125382 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.2020. Min Act: -0.1700
Data Index: 2969611 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.1707. Min Act: -0.1700
Data Index: 6327463 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6707. Min Range: -6.6707
Max Act: 6.1707. Min Act: -0.1700
Data Index: 8294208 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19