Model: None
Dataset: The Pile
Neuron 2082 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.0792. Min Range: -3.0792
Max Act: 3.0792. Min Act: -0.1700
Data Index: 1172948 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0792. Min Range: -3.0792
Max Act: 3.0792. Min Act: -0.1700
Data Index: 5614616 (The Pile)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0792. Min Range: -3.0792
Max Act: 3.0160. Min Act: -0.1700
Data Index: 7337926 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9686. Min Act: -0.1700
Data Index: 1383103 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9686. Min Act: -0.1700
Data Index: 1792109 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9528. Min Act: -0.1700
Data Index: 755466 (The Pile)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9369. Min Act: -0.1700
Data Index: 241976 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9369. Min Act: -0.1700
Data Index: 10576685 (The Pile)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9211. Min Act: -0.1700
Data Index: 2074507 (The Pile)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9211. Min Act: -0.1700
Data Index: 7923946 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9052. Min Act: -0.1700
Data Index: 585561 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9052. Min Act: -0.1700
Data Index: 3448766 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9052. Min Act: -0.1700
Data Index: 1510562 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9052. Min Act: -0.1700
Data Index: 7274935 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.9052. Min Act: -0.1700
Data Index: 2009188 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.8894. Min Act: -0.1700
Data Index: 5882935 (The Pile)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.8894. Min Act: -0.1700
Data Index: 2699030 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.8894. Min Act: -0.1700
Data Index: 1970091 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.8894. Min Act: -0.1700
Data Index: 10466017 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0792. Min Range: -3.0792
Max Act: 2.8894. Min Act: -0.1700
Data Index: 6560320 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19