Model: None
Dataset: The Pile
Neuron 2720 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.2757. Min Act: -0.1700
Data Index: 3000688 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.2757. Min Act: -0.1700
Data Index: 8730919 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.2132. Min Act: -0.1700
Data Index: 6768520 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1820. Min Act: -0.1700
Data Index: 6288369 (The Pile)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1820. Min Act: -0.1700
Data Index: 2939982 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1820. Min Act: -0.1700
Data Index: 5625387 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1507. Min Act: -0.1700
Data Index: 7702078 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1507. Min Act: -0.1700
Data Index: 979730 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1507. Min Act: -0.1700
Data Index: 8758613 (The Pile)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1195. Min Act: -0.1700
Data Index: 3076750 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1195. Min Act: -0.1700
Data Index: 4047974 (The Pile)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1195. Min Act: -0.1700
Data Index: 1997361 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1195. Min Act: -0.1700
Data Index: 3359250 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.1195. Min Act: -0.1700
Data Index: 3246181 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.0882. Min Act: -0.1700
Data Index: 10145568 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.0882. Min Act: -0.1700
Data Index: 2246362 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.0882. Min Act: -0.1700
Data Index: 678431 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.0882. Min Act: -0.1700
Data Index: 6304410 (The Pile)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.0882. Min Act: -0.1700
Data Index: 8197971 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2757. Min Range: -5.2757
Max Act: 5.0570. Min Act: -0.1700
Data Index: 4327568 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19