Model: None
Dataset: The Pile
Neuron 580 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.7878. Min Act: -0.1700
Data Index: 10028990 (The Pile)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.7559. Min Act: -0.1700
Data Index: 1020533 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.7399. Min Act: -0.1700
Data Index: 10389903 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.7239. Min Act: -0.1700
Data Index: 9921216 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.7239. Min Act: -0.1700
Data Index: 2724201 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.7079. Min Act: -0.1700
Data Index: 5907380 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6919. Min Act: -0.1700
Data Index: 484091 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6919. Min Act: -0.1700
Data Index: 9720758 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6919. Min Act: -0.1700
Data Index: 6187982 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6919. Min Act: -0.1700
Data Index: 5902603 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6919. Min Act: -0.1700
Data Index: 8316933 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6599. Min Act: -0.1700
Data Index: 8360223 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6599. Min Act: -0.1700
Data Index: 6155122 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6438. Min Act: -0.1700
Data Index: 10212736 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6438. Min Act: -0.1700
Data Index: 10346587 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6438. Min Act: -0.1700
Data Index: 956783 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6438. Min Act: -0.1700
Data Index: 5563011 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6438. Min Act: -0.1700
Data Index: 9105249 (The Pile)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6438. Min Act: -0.1700
Data Index: 7622904 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7878. Min Range: -2.7878
Max Act: 2.6438. Min Act: -0.1700
Data Index: 4776790 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #19