Model: None
Dataset: The Pile
Neuron 800 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 40054 (The Pile)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 84981 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 84581 (The Pile)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 80829 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 77909 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 72771 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 66839 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 65675 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 55333 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 48742 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 11754 (The Pile)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 39748 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 37434 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 37352 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 35595 (The Pile)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 33080 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 1162 (The Pile)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1699
Data Index: 21299 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 2719 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7763. Min Range: -1.7763
Max Act: 1.7763. Min Act: -0.1700
Data Index: 12908 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19