Model: None
Dataset: The Pile
Neuron 3070 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.2157. Min Act: -0.1700
Data Index: 6164963 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.2157. Min Act: -0.1700
Data Index: 7168182 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.1688. Min Act: -0.1700
Data Index: 5814438 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.1688. Min Act: -0.1700
Data Index: 9912636 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.1688. Min Act: -0.1700
Data Index: 1898377 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.1376. Min Act: -0.1700
Data Index: 8449108 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.1063. Min Act: -0.1700
Data Index: 2053838 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.1063. Min Act: -0.1700
Data Index: 3455686 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.0751. Min Act: -0.1700
Data Index: 3832394 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.0438. Min Act: -0.1700
Data Index: 1107311 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.0282. Min Act: -0.1700
Data Index: 979768 (The Pile)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.0125. Min Act: -0.1700
Data Index: 4092778 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.0125. Min Act: -0.1700
Data Index: 7457544 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2157. Min Range: -4.2157
Max Act: 4.0125. Min Act: -0.1700
Data Index: 2051092 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2157. Min Range: -4.2157
Max Act: 3.9969. Min Act: -0.1700
Data Index: 5944659 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2157. Min Range: -4.2157
Max Act: 3.9813. Min Act: -0.1700
Data Index: 2308760 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2157. Min Range: -4.2157
Max Act: 3.9813. Min Act: -0.1700
Data Index: 6977900 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2157. Min Range: -4.2157
Max Act: 3.9813. Min Act: -0.1700
Data Index: 989997 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2157. Min Range: -4.2157
Max Act: 3.9656. Min Act: -0.1700
Data Index: 9652590 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2157. Min Range: -4.2157
Max Act: 3.9500. Min Act: -0.1700
Data Index: 8558976 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19