Model: None
Dataset: The Pile
Neuron 1437 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.5365. Min Act: -0.1700
Data Index: 9951355 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.5365. Min Act: -0.1700
Data Index: 7400597 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.5203. Min Act: -0.1700
Data Index: 2085687 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.5041. Min Act: -0.1700
Data Index: 5316814 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.5041. Min Act: -0.1700
Data Index: 5873008 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4879. Min Act: -0.1700
Data Index: 1049287 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4879. Min Act: -0.1700
Data Index: 1184891 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4717. Min Act: -0.1700
Data Index: 5155818 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4717. Min Act: -0.1700
Data Index: 1607192 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4717. Min Act: -0.1700
Data Index: 6740110 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4717. Min Act: -0.1700
Data Index: 5434646 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4717. Min Act: -0.1700
Data Index: 6700142 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4717. Min Act: -0.1700
Data Index: 2363823 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4717. Min Act: -0.1699
Data Index: 5154462 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4717. Min Act: -0.1700
Data Index: 4866103 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4555. Min Act: -0.1700
Data Index: 774568 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4555. Min Act: -0.1700
Data Index: 6857548 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4555. Min Act: -0.1700
Data Index: 5634896 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4555. Min Act: -0.1700
Data Index: 6356676 (The Pile)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5365. Min Range: -2.5365
Max Act: 2.4555. Min Act: -0.1700
Data Index: 1482069 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19