Model: None
Dataset: The Pile
Neuron 1854 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.0389. Min Range: -4.0389
Max Act: 4.0389. Min Act: -0.1700
Data Index: 2367938 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0389. Min Range: -4.0389
Max Act: 4.0233. Min Act: -0.1700
Data Index: 4251595 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0389. Min Range: -4.0389
Max Act: 4.0077. Min Act: -0.1700
Data Index: 5808014 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.9764. Min Act: -0.1700
Data Index: 2299532 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.9608. Min Act: -0.1699
Data Index: 4552077 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.9608. Min Act: -0.1700
Data Index: 4735459 (The Pile)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.9139. Min Act: -0.1700
Data Index: 7959631 (The Pile)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.8982. Min Act: -0.1700
Data Index: 6491193 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.8982. Min Act: -0.1700
Data Index: 7419128 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.8513. Min Act: -0.1700
Data Index: 8838170 (The Pile)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.8357. Min Act: -0.1700
Data Index: 6310404 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.8357. Min Act: -0.1700
Data Index: 1136669 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.8201. Min Act: -0.1700
Data Index: 10249917 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.8201. Min Act: -0.1700
Data Index: 8228310 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.8044. Min Act: -0.1700
Data Index: 1622679 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.7731. Min Act: -0.1700
Data Index: 5833472 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.7731. Min Act: -0.1700
Data Index: 2126335 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.7731. Min Act: -0.1700
Data Index: 4570626 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.7731. Min Act: -0.1700
Data Index: 5219768 (The Pile)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0389. Min Range: -4.0389
Max Act: 3.7731. Min Act: -0.1700
Data Index: 5202998 (The Pile)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19