Model: None
Dataset: The Pile
Neuron 1985 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.2547. Min Range: -4.2547
Max Act: 4.2547. Min Act: -0.1700
Data Index: 6936465 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2547. Min Range: -4.2547
Max Act: 4.2234. Min Act: -0.1700
Data Index: 1838239 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2547. Min Range: -4.2547
Max Act: 4.1609. Min Act: -0.1700
Data Index: 8828791 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2547. Min Range: -4.2547
Max Act: 4.0359. Min Act: -0.1700
Data Index: 6932910 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2547. Min Range: -4.2547
Max Act: 4.0202. Min Act: -0.1700
Data Index: 3921758 (The Pile)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.8795. Min Act: -0.1700
Data Index: 2679349 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.8639. Min Act: -0.1700
Data Index: 3506527 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.8483. Min Act: -0.1700
Data Index: 1650440 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.8483. Min Act: -0.1700
Data Index: 1948954 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.8326. Min Act: -0.1700
Data Index: 3000758 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.8170. Min Act: -0.1700
Data Index: 6733571 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.8013. Min Act: -0.1700
Data Index: 8884309 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.7857. Min Act: -0.1700
Data Index: 2629623 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.7857. Min Act: -0.1700
Data Index: 5620707 (The Pile)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.7857. Min Act: -0.1700
Data Index: 10425663 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.7857. Min Act: -0.1700
Data Index: 9284039 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.7701. Min Act: -0.1700
Data Index: 2833267 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.7701. Min Act: -0.1700
Data Index: 4091916 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.7701. Min Act: -0.1700
Data Index: 1599420 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2547. Min Range: -4.2547
Max Act: 3.7701. Min Act: -0.1700
Data Index: 7559637 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19