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

Dataset: The Pile

Neuron 200 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1627677 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4941. Min Act: -0.0000

Data Index: 595388 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4503. Min Act: -0.0000

Data Index: 310072 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1224759 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1311563 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1682508 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1933658 (The Pile)

Max Activating Token Index: 806

Text #7

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1964681 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1431404 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3665. Min Act: -0.0000

Data Index: 35949 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1382374 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3335. Min Act: -0.0000

Data Index: 889308 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1862993 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3275. Min Act: -0.0000

Data Index: 508118 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3370. Min Act: -0.0000

Data Index: 128255 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3456. Min Act: -0.0000

Data Index: 413530 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3327. Min Act: -0.0000

Data Index: 1173433 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3190. Min Act: -0.0000

Data Index: 758794 (The Pile)

Max Activating Token Index: 54

Text #18

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1180154 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3068. Min Act: -0.0000

Data Index: 298891 (The Pile)

Max Activating Token Index: 381