Model: None
Dataset: The Pile
Neuron 478 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.9316. Min Act: -0.1700
Data Index: 9395048 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.9316. Min Act: -0.1700
Data Index: 1755888 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.9158. Min Act: -0.1700
Data Index: 2529590 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8999. Min Act: -0.1700
Data Index: 8971823 (The Pile)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8999. Min Act: -0.1700
Data Index: 4110067 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8999. Min Act: -0.1700
Data Index: 2196100 (The Pile)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8999. Min Act: -0.1700
Data Index: 8613308 (The Pile)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.9158. Min Act: -0.1700
Data Index: 141473 (The Pile)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8841. Min Act: -0.1700
Data Index: 927796 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8841. Min Act: -0.1700
Data Index: 10741854 (The Pile)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8999. Min Act: -0.1700
Data Index: 9732842 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8841. Min Act: -0.1700
Data Index: 5469290 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8682. Min Act: -0.1700
Data Index: 2826752 (The Pile)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8682. Min Act: -0.1700
Data Index: 5878644 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8523. Min Act: -0.1700
Data Index: 6352594 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8682. Min Act: -0.1700
Data Index: 1047544 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8523. Min Act: -0.1700
Data Index: 10601980 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8682. Min Act: -0.1700
Data Index: 8320342 (The Pile)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8205. Min Act: -0.1700
Data Index: 7064293 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9316. Min Range: -2.9316
Max Act: 2.8364. Min Act: -0.1700
Data Index: 2515408 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19