Model: None
Dataset: The Pile
Neuron 347 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.6473. Min Act: -0.1700
Data Index: 10395704 (The Pile)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5690. Min Act: -0.1700
Data Index: 3315358 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5690. Min Act: -0.1700
Data Index: 7210720 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5690. Min Act: -0.1700
Data Index: 5085845 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5690. Min Act: -0.1700
Data Index: 7062765 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5377. Min Act: -0.1700
Data Index: 3489125 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5377. Min Act: -0.1700
Data Index: 10003482 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5220. Min Act: -0.1700
Data Index: 5139289 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5220. Min Act: -0.1700
Data Index: 6203571 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5220. Min Act: -0.1700
Data Index: 7624909 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5220. Min Act: -0.1700
Data Index: 1464855 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5064. Min Act: -0.1700
Data Index: 5091881 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5064. Min Act: -0.1700
Data Index: 9772248 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.5064. Min Act: -0.1700
Data Index: 7524045 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4907. Min Act: -0.1700
Data Index: 4672801 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4750. Min Act: -0.1700
Data Index: 7053673 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4750. Min Act: -0.1700
Data Index: 2532060 (The Pile)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4750. Min Act: -0.1700
Data Index: 3530157 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4750. Min Act: -0.1700
Data Index: 2061079 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6473. Min Range: -3.6473
Max Act: 3.4594. Min Act: -0.1700
Data Index: 4839423 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19