Model: None
Dataset: The Pile
Neuron 1706 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.6679. Min Act: -0.1700
Data Index: 4225778 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.6523. Min Act: -0.1700
Data Index: 9877569 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.6366. Min Act: -0.1700
Data Index: 9697167 (The Pile)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.6053. Min Act: -0.1700
Data Index: 10254158 (The Pile)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.5740. Min Act: -0.1700
Data Index: 4629582 (The Pile)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.5740. Min Act: -0.1700
Data Index: 1245802 (The Pile)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.5583. Min Act: -0.1700
Data Index: 8775593 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.5583. Min Act: -0.1700
Data Index: 999157 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.5270. Min Act: -0.1700
Data Index: 1305925 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.5270. Min Act: -0.1700
Data Index: 10303968 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.5113. Min Act: -0.1700
Data Index: 6416846 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4957. Min Act: -0.1700
Data Index: 8200364 (The Pile)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4957. Min Act: -0.1700
Data Index: 2544730 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4957. Min Act: -0.1700
Data Index: 4995428 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4800. Min Act: -0.1699
Data Index: 9279984 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4800. Min Act: -0.1700
Data Index: 391619 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4800. Min Act: -0.1700
Data Index: 1820270 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4643. Min Act: -0.1700
Data Index: 8528992 (The Pile)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4643. Min Act: -0.1700
Data Index: 4874022 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6679. Min Range: -3.6679
Max Act: 3.4643. Min Act: -0.1700
Data Index: 4680963 (The Pile)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19