Model: None
Dataset: The Pile
Neuron 2110 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.7886. Min Act: -0.1700
Data Index: 1329864 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.7726. Min Act: -0.1700
Data Index: 282302 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.7248. Min Act: -0.1700
Data Index: 2059257 (The Pile)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.7248. Min Act: -0.1700
Data Index: 5963993 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.7248. Min Act: -0.1700
Data Index: 5983996 (The Pile)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.7088. Min Act: -0.1700
Data Index: 10645640 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.7088. Min Act: -0.1700
Data Index: 10040280 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6928. Min Act: -0.1700
Data Index: 8031675 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6928. Min Act: -0.1700
Data Index: 1507377 (The Pile)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6767. Min Act: -0.1700
Data Index: 5464571 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6767. Min Act: -0.1700
Data Index: 10510791 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6607. Min Act: -0.1700
Data Index: 479322 (The Pile)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6607. Min Act: -0.1700
Data Index: 6272799 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6607. Min Act: -0.1700
Data Index: 10607907 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6607. Min Act: -0.1700
Data Index: 3087137 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6447. Min Act: -0.1700
Data Index: 8941762 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6447. Min Act: -0.1700
Data Index: 5065203 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6447. Min Act: -0.1700
Data Index: 10668965 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6286. Min Act: -0.1700
Data Index: 8444820 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7886. Min Range: -2.7886
Max Act: 2.6286. Min Act: -0.1700
Data Index: 5042207 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19