Model: None
Dataset: The Pile
Neuron 1989 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.1907. Min Act: -0.1700
Data Index: 1599952 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.1435. Min Act: -0.1700
Data Index: 5491458 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0962. Min Act: -0.1700
Data Index: 4920583 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0962. Min Act: -0.1700
Data Index: 6856671 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0804. Min Act: -0.1700
Data Index: 2975371 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0804. Min Act: -0.1700
Data Index: 10688711 (The Pile)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0804. Min Act: -0.1700
Data Index: 3155269 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0804. Min Act: -0.1700
Data Index: 10429148 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0646. Min Act: -0.1700
Data Index: 7502202 (The Pile)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0646. Min Act: -0.1700
Data Index: 5975709 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0489. Min Act: -0.1700
Data Index: 6136364 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0489. Min Act: -0.1700
Data Index: 6966195 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0489. Min Act: -0.1700
Data Index: 6899935 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0331. Min Act: -0.1700
Data Index: 4806254 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0331. Min Act: -0.1700
Data Index: 4585066 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0331. Min Act: -0.1700
Data Index: 1604792 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0173. Min Act: -0.1700
Data Index: 10134472 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0015. Min Act: -0.1700
Data Index: 9265351 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0015. Min Act: -0.1700
Data Index: 10121031 (The Pile)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1907. Min Range: -3.1907
Max Act: 3.0015. Min Act: -0.1700
Data Index: 4332595 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19