Model: None
Dataset: The Pile
Neuron 3575 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2906. Min Act: -0.1700
Data Index: 6334217 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2591. Min Act: -0.1700
Data Index: 864832 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2591. Min Act: -0.1700
Data Index: 4834671 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2434. Min Act: -0.1700
Data Index: 1473723 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2434. Min Act: -0.1700
Data Index: 5823107 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2434. Min Act: -0.1700
Data Index: 3209041 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2277. Min Act: -0.1700
Data Index: 7852549 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2277. Min Act: -0.1700
Data Index: 8912996 (The Pile)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.2120. Min Act: -0.1700
Data Index: 4419722 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1805. Min Act: -0.1700
Data Index: 5785971 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1490. Min Act: -0.1700
Data Index: 6867443 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1333. Min Act: -0.1700
Data Index: 7551292 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1333. Min Act: -0.1700
Data Index: 1860207 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1333. Min Act: -0.1700
Data Index: 1264509 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1333. Min Act: -0.1700
Data Index: 2101995 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1017. Min Act: -0.1700
Data Index: 9672700 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1017. Min Act: -0.1700
Data Index: 670041 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.1017. Min Act: -0.1700
Data Index: 2077866 (The Pile)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.0860. Min Act: -0.1700
Data Index: 3490986 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2906. Min Range: -3.2906
Max Act: 3.0860. Min Act: -0.1700
Data Index: 8298970 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19