Model: None
Dataset: The Pile
Neuron 2631 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.6111. Min Act: -0.1700
Data Index: 2016557 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.5485. Min Act: -0.1700
Data Index: 2589804 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.4545. Min Act: -0.1700
Data Index: 5530465 (The Pile)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.4231. Min Act: -0.1700
Data Index: 593576 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.4075. Min Act: -0.1700
Data Index: 7770229 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.4075. Min Act: -0.1700
Data Index: 5188370 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.4075. Min Act: -0.1700
Data Index: 1187907 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3761. Min Act: -0.1700
Data Index: 807082 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3761. Min Act: -0.1700
Data Index: 3506025 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3604. Min Act: -0.1700
Data Index: 7425860 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3447. Min Act: -0.1700
Data Index: 3670659 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3447. Min Act: -0.1700
Data Index: 882553 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3447. Min Act: -0.1700
Data Index: 8449443 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3447. Min Act: -0.1700
Data Index: 6860915 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3447. Min Act: -0.1700
Data Index: 8220116 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3447. Min Act: -0.1700
Data Index: 3600984 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3290. Min Act: -0.1700
Data Index: 4647507 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3290. Min Act: -0.1700
Data Index: 78285 (The Pile)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3290. Min Act: -0.1700
Data Index: 7941482 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6111. Min Range: -3.6111
Max Act: 3.3290. Min Act: -0.1700
Data Index: 9207965 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19