Model: None
Dataset: The Pile
Neuron 3893 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.6654. Min Act: -0.1700
Data Index: 7557976 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.6333. Min Act: -0.1700
Data Index: 122354 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.6333. Min Act: -0.1700
Data Index: 7510751 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.5528. Min Act: -0.1700
Data Index: 1492392 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.5367. Min Act: -0.1700
Data Index: 3022960 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.5205. Min Act: -0.1700
Data Index: 6040143 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.5205. Min Act: -0.1700
Data Index: 2887093 (The Pile)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.5205. Min Act: -0.1700
Data Index: 1621967 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.5043. Min Act: -0.1700
Data Index: 9595984 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.5043. Min Act: -0.1700
Data Index: 7544100 (The Pile)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4881. Min Act: -0.1700
Data Index: 8292292 (The Pile)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4881. Min Act: -0.1700
Data Index: 10147428 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4881. Min Act: -0.1700
Data Index: 932622 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4881. Min Act: -0.1700
Data Index: 4223827 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4719. Min Act: -0.1700
Data Index: 5688235 (The Pile)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4719. Min Act: -0.1700
Data Index: 4682532 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4719. Min Act: -0.1700
Data Index: 1092325 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4719. Min Act: -0.1700
Data Index: 9269411 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4719. Min Act: -0.1700
Data Index: 8654822 (The Pile)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6654. Min Range: -2.6654
Max Act: 2.4557. Min Act: -0.1700
Data Index: 797126 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19