Model: None
Dataset: The Pile
Neuron 3506 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.7834. Min Act: -0.1700
Data Index: 1086909 (The Pile)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.7209. Min Act: -0.1700
Data Index: 3255378 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.7209. Min Act: -0.1700
Data Index: 4654060 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.6739. Min Act: -0.1700
Data Index: 3551114 (The Pile)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.6583. Min Act: -0.1700
Data Index: 4109231 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.5643. Min Act: -0.1700
Data Index: 5822335 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.5487. Min Act: -0.1700
Data Index: 5912032 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.5487. Min Act: -0.1700
Data Index: 6205661 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4547. Min Act: -0.1700
Data Index: 3315016 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4547. Min Act: -0.1700
Data Index: 3010071 (The Pile)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4390. Min Act: -0.1700
Data Index: 959492 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4390. Min Act: -0.1700
Data Index: 6364859 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4233. Min Act: -0.1700
Data Index: 9207068 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4233. Min Act: -0.1700
Data Index: 1819573 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4076. Min Act: -0.1700
Data Index: 10324051 (The Pile)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4076. Min Act: -0.1700
Data Index: 2872636 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4076. Min Act: -0.1700
Data Index: 7251892 (The Pile)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4076. Min Act: -0.1700
Data Index: 2558285 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.4076. Min Act: -0.1700
Data Index: 3962126 (The Pile)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7834. Min Range: -3.7834
Max Act: 3.3919. Min Act: -0.1700
Data Index: 2999017 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19