Model: None
Dataset: The Pile
Neuron 2762 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.0412. Min Range: -3.0412
Max Act: 3.0412. Min Act: -0.1700
Data Index: 3922174 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0412. Min Range: -3.0412
Max Act: 3.0412. Min Act: -0.1700
Data Index: 7468119 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0412. Min Range: -3.0412
Max Act: 3.0096. Min Act: -0.1700
Data Index: 150041 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9622. Min Act: -0.1700
Data Index: 9789674 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9463. Min Act: -0.1700
Data Index: 1987407 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9463. Min Act: -0.1700
Data Index: 7611473 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9305. Min Act: -0.1700
Data Index: 4933140 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9305. Min Act: -0.1700
Data Index: 4274597 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9305. Min Act: -0.1700
Data Index: 1454530 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9305. Min Act: -0.1700
Data Index: 9242250 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9305. Min Act: -0.1700
Data Index: 115493 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9305. Min Act: -0.1700
Data Index: 3386488 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.9146. Min Act: -0.1700
Data Index: 10609088 (The Pile)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.8988. Min Act: -0.1700
Data Index: 1754843 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.8829. Min Act: -0.1700
Data Index: 5200428 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.8829. Min Act: -0.1700
Data Index: 941025 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.8829. Min Act: -0.1700
Data Index: 5816248 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.8829. Min Act: -0.1700
Data Index: 9639766 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.8829. Min Act: -0.1700
Data Index: 1916913 (The Pile)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0412. Min Range: -3.0412
Max Act: 2.8829. Min Act: -0.1700
Data Index: 10339994 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19