Model: None
Dataset: The Pile
Neuron 470 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.4707. Min Act: -0.1700
Data Index: 1685585 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.4382. Min Act: -0.1700
Data Index: 9411626 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.4219. Min Act: -0.1700
Data Index: 9145232 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.4219. Min Act: -0.1700
Data Index: 261978 (The Pile)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3730. Min Act: -0.1700
Data Index: 4097146 (The Pile)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.4382. Min Act: -0.1700
Data Index: 221023 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3893. Min Act: -0.1700
Data Index: 10630203 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3566. Min Act: -0.1700
Data Index: 5209473 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.4056. Min Act: -0.1700
Data Index: 956920 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3730. Min Act: -0.1700
Data Index: 10404208 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3730. Min Act: -0.1700
Data Index: 3748404 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3566. Min Act: -0.1700
Data Index: 5898546 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3730. Min Act: -0.1700
Data Index: 2534942 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3239. Min Act: -0.1700
Data Index: 8117446 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3566. Min Act: -0.1700
Data Index: 4177515 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3730. Min Act: -0.1700
Data Index: 1821281 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3893. Min Act: -0.1700
Data Index: 6908072 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3566. Min Act: -0.1700
Data Index: 3203461 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3566. Min Act: -0.1700
Data Index: 163596 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4707. Min Range: -2.4707
Max Act: 2.3566. Min Act: -0.1700
Data Index: 1612678 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19