Model: None
Dataset: The Pile
Neuron 792 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.0692. Min Range: -3.0692
Max Act: 3.0692. Min Act: -0.1700
Data Index: 7381416 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0692. Min Range: -3.0692
Max Act: 3.0376. Min Act: -0.1700
Data Index: 8446849 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0692. Min Range: -3.0692
Max Act: 3.0060. Min Act: -0.1700
Data Index: 3000100 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9744. Min Act: -0.1700
Data Index: 9086025 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9427. Min Act: -0.1700
Data Index: 2728931 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9269. Min Act: -0.1700
Data Index: 149979 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9269. Min Act: -0.1700
Data Index: 1836477 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9269. Min Act: -0.1700
Data Index: 4290868 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9269. Min Act: -0.1700
Data Index: 5656337 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9269. Min Act: -0.1700
Data Index: 4515891 (The Pile)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9110. Min Act: -0.1700
Data Index: 721050 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9110. Min Act: -0.1700
Data Index: 3520782 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.9110. Min Act: -0.1700
Data Index: 8514419 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.8952. Min Act: -0.1700
Data Index: 673800 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.8952. Min Act: -0.1700
Data Index: 7289963 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.8952. Min Act: -0.1700
Data Index: 1387325 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.8952. Min Act: -0.1700
Data Index: 4576052 (The Pile)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.8952. Min Act: -0.1700
Data Index: 1222543 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.8793. Min Act: -0.1700
Data Index: 2605123 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0692. Min Range: -3.0692
Max Act: 2.8793. Min Act: -0.1700
Data Index: 4461951 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19