Model: None
Dataset: The Pile
Neuron 1702 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7991. Min Act: -0.1700
Data Index: 6428364 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7834. Min Act: -0.1700
Data Index: 7222708 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7678. Min Act: -0.1700
Data Index: 738805 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7521. Min Act: -0.1700
Data Index: 703023 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7365. Min Act: -0.1700
Data Index: 5688284 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7365. Min Act: -0.1700
Data Index: 579407 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.7208. Min Act: -0.1700
Data Index: 5723925 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6895. Min Act: -0.1700
Data Index: 7572559 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6895. Min Act: -0.1700
Data Index: 3864599 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6895. Min Act: -0.1700
Data Index: 1383358 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6739. Min Act: -0.1700
Data Index: 976273 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6739. Min Act: -0.1700
Data Index: 3430071 (The Pile)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6582. Min Act: -0.1700
Data Index: 9201639 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6582. Min Act: -0.1700
Data Index: 6804929 (The Pile)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6582. Min Act: -0.1700
Data Index: 385555 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6582. Min Act: -0.1700
Data Index: 7341563 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6426. Min Act: -0.1700
Data Index: 3683148 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6426. Min Act: -0.1700
Data Index: 9530854 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6426. Min Act: -0.1700
Data Index: 201606 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7991. Min Range: -3.7991
Max Act: 3.6426. Min Act: -0.1700
Data Index: 9622640 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19