Model: None
Dataset: The Pile
Neuron 34 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 11.4281. Min Range: -11.4281
Max Act: 11.4281. Min Act: -0.1700
Data Index: 1464828 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4281. Min Range: -11.4281
Max Act: 11.3656. Min Act: -0.1700
Data Index: 7697686 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4281. Min Range: -11.4281
Max Act: 11.3656. Min Act: -0.1700
Data Index: 7421702 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4281. Min Range: -11.4281
Max Act: 11.1156. Min Act: -0.1700
Data Index: 10491013 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4281. Min Range: -11.4281
Max Act: 11.0531. Min Act: -0.1700
Data Index: 1853529 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.8656. Min Act: -0.1700
Data Index: 10239001 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.8656. Min Act: -0.1700
Data Index: 10786276 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.8656. Min Act: -0.1700
Data Index: 2636668 (The Pile)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.8031. Min Act: -0.1700
Data Index: 6512268 (The Pile)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.8031. Min Act: -0.1700
Data Index: 2374945 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.8031. Min Act: -0.1700
Data Index: 7482063 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.7406. Min Act: -0.1700
Data Index: 9659458 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.7406. Min Act: -0.1700
Data Index: 8850499 (The Pile)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.7406. Min Act: -0.1700
Data Index: 6243566 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.7406. Min Act: -0.1700
Data Index: 6035484 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.7406. Min Act: -0.1700
Data Index: 2388108 (The Pile)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.7406. Min Act: -0.1700
Data Index: 659968 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.6781. Min Act: -0.1700
Data Index: 6298109 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.6781. Min Act: -0.1700
Data Index: 4876153 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4281. Min Range: -11.4281
Max Act: 10.6781. Min Act: -0.1700
Data Index: 8034659 (The Pile)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19