Model: None
Dataset: The Pile
Neuron 350 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.1749. Min Act: -0.1700
Data Index: 7081478 (The Pile)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.0488. Min Act: -0.1699
Data Index: 407115 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.0172. Min Act: -0.1700
Data Index: 6610770 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.0330. Min Act: -0.1700
Data Index: 7543522 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.0014. Min Act: -0.1700
Data Index: 1538666 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.0488. Min Act: -0.1700
Data Index: 5307468 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.0014. Min Act: -0.1700
Data Index: 3357359 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.0172. Min Act: -0.1700
Data Index: 4156597 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9698. Min Act: -0.1700
Data Index: 8468231 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9856. Min Act: -0.1700
Data Index: 4533555 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1749. Min Range: -3.1749
Max Act: 3.0014. Min Act: -0.1699
Data Index: 8514141 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9540. Min Act: -0.1700
Data Index: 9689906 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9698. Min Act: -0.1700
Data Index: 1665161 (The Pile)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9698. Min Act: -0.1700
Data Index: 8373537 (The Pile)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9540. Min Act: -0.1700
Data Index: 2335781 (The Pile)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9698. Min Act: -0.1700
Data Index: 5477691 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9540. Min Act: -0.1699
Data Index: 6652924 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9540. Min Act: -0.1700
Data Index: 4479026 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9540. Min Act: -0.1699
Data Index: 5093368 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1749. Min Range: -3.1749
Max Act: 2.9540. Min Act: -0.1700
Data Index: 5207304 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19