Model: None
Dataset: The Pile
Neuron 836 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.7266. Min Act: -0.1700
Data Index: 9716930 (The Pile)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.7109. Min Act: -0.1700
Data Index: 10293904 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.7109. Min Act: -0.1700
Data Index: 4384459 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.6327. Min Act: -0.1700
Data Index: 1433369 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.6327. Min Act: -0.1700
Data Index: 7863943 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.6170. Min Act: -0.1700
Data Index: 2900283 (The Pile)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.6170. Min Act: -0.1700
Data Index: 9224507 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5857. Min Act: -0.1700
Data Index: 10636234 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5701. Min Act: -0.1700
Data Index: 8274852 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5544. Min Act: -0.1700
Data Index: 5291854 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5544. Min Act: -0.1700
Data Index: 7868298 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5544. Min Act: -0.1700
Data Index: 9556452 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5544. Min Act: -0.1700
Data Index: 2164378 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5387. Min Act: -0.1700
Data Index: 3885644 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5387. Min Act: -0.1700
Data Index: 8350379 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5387. Min Act: -0.1700
Data Index: 7623944 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5231. Min Act: -0.1700
Data Index: 4532602 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5231. Min Act: -0.1696
Data Index: 3803835 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5231. Min Act: -0.1700
Data Index: 7044840 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7266. Min Range: -3.7266
Max Act: 3.5074. Min Act: -0.1700
Data Index: 2026194 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19