Model: None
Dataset: The Pile
Neuron 2512 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.7402. Min Act: -0.1700
Data Index: 5105326 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.6464. Min Act: -0.1700
Data Index: 8222633 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.5681. Min Act: -0.1700
Data Index: 4959468 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.5524. Min Act: -0.1700
Data Index: 3304410 (The Pile)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4741. Min Act: -0.1700
Data Index: 3857265 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4741. Min Act: -0.1700
Data Index: 1639035 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4427. Min Act: -0.1700
Data Index: 5431927 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4270. Min Act: -0.1700
Data Index: 6300220 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4114. Min Act: -0.1700
Data Index: 5066966 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.4114. Min Act: -0.1700
Data Index: 2161609 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3957. Min Act: -0.1700
Data Index: 3430524 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3800. Min Act: -0.1700
Data Index: 9506652 (The Pile)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3800. Min Act: -0.1700
Data Index: 697380 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3800. Min Act: -0.1700
Data Index: 6820766 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3800. Min Act: -0.1700
Data Index: 4704353 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3800. Min Act: -0.1700
Data Index: 5417987 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3643. Min Act: -0.1700
Data Index: 8183961 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3643. Min Act: -0.1700
Data Index: 9763417 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3486. Min Act: -0.1700
Data Index: 3862257 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7402. Min Range: -3.7402
Max Act: 3.3486. Min Act: -0.1700
Data Index: 1401153 (The Pile)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19