Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3341 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.3967. Min Act: -0.0000

Data Index: 1004220 (The Pile)

Max Activating Token Index: 268

Text #1

Max Range: 1.3967. Min Range: -1.3967

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1912014 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.9373. Min Act: -0.0000

Data Index: 4589 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.7118. Min Act: -0.0000

Data Index: 2377 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1218878 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1015173 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6701. Min Act: -0.0000

Data Index: 747293 (The Pile)

Max Activating Token Index: 932

Text #7

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.7114. Min Act: -0.0000

Data Index: 390355 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1810561 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6786. Min Act: -0.0000

Data Index: 412722 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1457182 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1595978 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1690878 (The Pile)

Max Activating Token Index: 748

Text #13

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1066323 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1942669 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6421. Min Act: -0.0000

Data Index: 515152 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6101. Min Act: -0.0000

Data Index: 710477 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6633. Min Act: -0.0000

Data Index: 421793 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6293. Min Act: -0.0000

Data Index: 809587 (The Pile)

Max Activating Token Index: 421

Text #19

Max Range: 1.3967. Min Range: -1.3967

Max Act: 0.6239. Min Act: -0.0000

Data Index: 821961 (The Pile)

Max Activating Token Index: 412