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

Dataset: The Pile

Neuron 507 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: 0.4519. Min Range: -0.4519

Max Act: 0.4485. Min Act: -0.0000

Data Index: 611877 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4519. Min Act: -0.0000

Data Index: 808221 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4085. Min Act: -0.0000

Data Index: 389992 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3797. Min Act: -0.0000

Data Index: 682794 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3737. Min Act: -0.0000

Data Index: 315326 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1748851 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3700. Min Act: -0.0000

Data Index: 1522347 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1090690 (The Pile)

Max Activating Token Index: 18

Text #8

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1457243 (The Pile)

Max Activating Token Index: 124

Text #9

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3476. Min Act: -0.0000

Data Index: 1310106 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3491. Min Act: -0.0000

Data Index: 939326 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1798254 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3292. Min Act: -0.0000

Data Index: 295270 (The Pile)

Max Activating Token Index: 30

Text #13

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3344. Min Act: -0.0000

Data Index: 765187 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3231. Min Act: -0.0000

Data Index: 649010 (The Pile)

Max Activating Token Index: 8

Text #15

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3225. Min Act: -0.0000

Data Index: 912712 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3225. Min Act: -0.0000

Data Index: 884039 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3417. Min Act: -0.0000

Data Index: 430876 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3313. Min Act: -0.0000

Data Index: 511135 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3290. Min Act: -0.0000

Data Index: 886840 (The Pile)

Max Activating Token Index: 13