Model: None
Dataset: The Pile
Neuron 657 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.5132. Min Act: -0.1700
Data Index: 964892 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.5456. Min Act: -0.1700
Data Index: 66753 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.5132. Min Act: -0.1699
Data Index: 2034857 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.5294. Min Act: -0.1700
Data Index: 8143845 (The Pile)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.5294. Min Act: -0.1700
Data Index: 8878448 (The Pile)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4971. Min Act: -0.1700
Data Index: 4599094 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.5132. Min Act: -0.1700
Data Index: 6121395 (The Pile)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.5294. Min Act: -0.1700
Data Index: 4190506 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4971. Min Act: -0.1699
Data Index: 7589327 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4971. Min Act: -0.1700
Data Index: 9849917 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4808. Min Act: -0.1700
Data Index: 5089934 (The Pile)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4808. Min Act: -0.1700
Data Index: 8676166 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.5132. Min Act: -0.1700
Data Index: 8777314 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4646. Min Act: -0.1700
Data Index: 1279914 (The Pile)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4971. Min Act: -0.1700
Data Index: 9889765 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4971. Min Act: -0.1700
Data Index: 150617 (The Pile)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4808. Min Act: -0.1700
Data Index: 4436401 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4971. Min Act: -0.1700
Data Index: 5945496 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4646. Min Act: -0.1700
Data Index: 6062723 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5456. Min Range: -2.5456
Max Act: 2.4646. Min Act: -0.1700
Data Index: 161349 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19