Model: None
Dataset: The Pile
Neuron 648 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.5389. Min Act: -0.1700
Data Index: 4917414 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4903. Min Act: -0.1700
Data Index: 9319390 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4741. Min Act: -0.1700
Data Index: 5022657 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4579. Min Act: -0.1700
Data Index: 6930943 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4254. Min Act: -0.1700
Data Index: 2014840 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4579. Min Act: -0.1700
Data Index: 8945089 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4416. Min Act: -0.1700
Data Index: 8344510 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4579. Min Act: -0.1700
Data Index: 3306104 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4254. Min Act: -0.1700
Data Index: 1618612 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4416. Min Act: -0.1700
Data Index: 5581936 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4254. Min Act: -0.1699
Data Index: 2759408 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.3928. Min Act: -0.1700
Data Index: 1042270 (The Pile)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4091. Min Act: -0.1700
Data Index: 9422229 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.3928. Min Act: -0.1700
Data Index: 5388549 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.3928. Min Act: -0.1700
Data Index: 3468467 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.3764. Min Act: -0.1700
Data Index: 3615878 (The Pile)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4091. Min Act: -0.1700
Data Index: 6638913 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.4091. Min Act: -0.1700
Data Index: 5854657 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.3601. Min Act: -0.1700
Data Index: 3112045 (The Pile)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5389. Min Range: -2.5389
Max Act: 2.3928. Min Act: -0.1698
Data Index: 9023013 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19