Model: None
Dataset: The Pile
Neuron 1575 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.6346. Min Act: -0.1700
Data Index: 8609310 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.6185. Min Act: -0.1700
Data Index: 5340272 (The Pile)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.6024. Min Act: -0.1700
Data Index: 2406843 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.6024. Min Act: -0.1700
Data Index: 2985286 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5863. Min Act: -0.1700
Data Index: 4319107 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5702. Min Act: -0.1700
Data Index: 8401579 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5702. Min Act: -0.1700
Data Index: 3733719 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5541. Min Act: -0.1700
Data Index: 1281426 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5541. Min Act: -0.1700
Data Index: 8674530 (The Pile)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5379. Min Act: -0.1700
Data Index: 6053770 (The Pile)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5379. Min Act: -0.1700
Data Index: 798166 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5379. Min Act: -0.1700
Data Index: 7032676 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5218. Min Act: -0.1700
Data Index: 4561821 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5218. Min Act: -0.1700
Data Index: 3051705 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5218. Min Act: -0.1700
Data Index: 6343207 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5218. Min Act: -0.1700
Data Index: 5671038 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5218. Min Act: -0.1700
Data Index: 6467338 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5218. Min Act: -0.1700
Data Index: 7558853 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5218. Min Act: -0.1700
Data Index: 6768832 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6346. Min Range: -2.6346
Max Act: 2.5218. Min Act: -0.1700
Data Index: 917121 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19