Model: None
Dataset: The Pile
Neuron 20 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.5328. Min Act: -0.1700
Data Index: 2752457 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.5328. Min Act: -0.1700
Data Index: 4394984 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.5328. Min Act: -0.1700
Data Index: 3003373 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.5328. Min Act: -0.1700
Data Index: 7855332 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.5328. Min Act: -0.1700
Data Index: 7136768 (The Pile)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.5166. Min Act: -0.1700
Data Index: 6630799 (The Pile)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.5004. Min Act: -0.1700
Data Index: 491049 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4842. Min Act: -0.1700
Data Index: 10795431 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4842. Min Act: -0.1699
Data Index: 3977453 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4680. Min Act: -0.1699
Data Index: 7512292 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4517. Min Act: -0.1700
Data Index: 5290116 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4517. Min Act: -0.1700
Data Index: 6047595 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4517. Min Act: -0.1700
Data Index: 8760633 (The Pile)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4517. Min Act: -0.1700
Data Index: 4196915 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4517. Min Act: -0.1699
Data Index: 4584953 (The Pile)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4517. Min Act: -0.1700
Data Index: 2072764 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4355. Min Act: -0.1700
Data Index: 6730152 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4355. Min Act: -0.1700
Data Index: 778967 (The Pile)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4355. Min Act: -0.1699
Data Index: 3666419 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5328. Min Range: -2.5328
Max Act: 2.4355. Min Act: -0.1700
Data Index: 3401341 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19