Model: None
Dataset: The Pile
Neuron 3805 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.8594. Min Act: -0.1700
Data Index: 3594784 (The Pile)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.7499. Min Act: -0.1700
Data Index: 9380000 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.7499. Min Act: -0.1700
Data Index: 7744218 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.7186. Min Act: -0.1700
Data Index: 8461883 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.7186. Min Act: -0.1700
Data Index: 6175555 (The Pile)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.7029. Min Act: -0.1700
Data Index: 9042544 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.7029. Min Act: -0.1700
Data Index: 7815105 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.7029. Min Act: -0.1700
Data Index: 1926751 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6873. Min Act: -0.1700
Data Index: 3439973 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6716. Min Act: -0.1700
Data Index: 3187869 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6716. Min Act: -0.1700
Data Index: 8222622 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6560. Min Act: -0.1700
Data Index: 3041444 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6403. Min Act: -0.1700
Data Index: 5557296 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6403. Min Act: -0.1700
Data Index: 5396526 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6247. Min Act: -0.1700
Data Index: 10268359 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6247. Min Act: -0.1700
Data Index: 8005961 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6247. Min Act: -0.1700
Data Index: 8746087 (The Pile)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6247. Min Act: -0.1700
Data Index: 2175271 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6090. Min Act: -0.1700
Data Index: 4305034 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8594. Min Range: -3.8594
Max Act: 3.6090. Min Act: -0.1700
Data Index: 6942312 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19