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

Dataset: The Pile

Neuron 2943 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: 0.6894. Min Range: -0.6894

Max Act: 0.6894. Min Act: -0.0000

Data Index: 963355 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.6521. Min Act: -0.0000

Data Index: 167653 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1078591 (The Pile)

Max Activating Token Index: 524

Text #3

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5057. Min Act: -0.0000

Data Index: 1611279 (The Pile)

Max Activating Token Index: 743

Text #4

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4909. Min Act: 0.0000

Data Index: 4179 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4717. Min Act: -0.0000

Data Index: 661214 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4303. Min Act: -0.0000

Data Index: 725794 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1323215 (The Pile)

Max Activating Token Index: 195

Text #8

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1214000 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.5082. Min Act: -0.0000

Data Index: 547449 (The Pile)

Max Activating Token Index: 992

Text #10

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4455. Min Act: 0.0000

Data Index: 1994993 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4428. Min Act: -0.0000

Data Index: 324235 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4385. Min Act: 0.0000

Data Index: 1702319 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1922495 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4223. Min Act: -0.0000

Data Index: 223631 (The Pile)

Max Activating Token Index: 659

Text #15

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1825314 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4194. Min Act: 0.0000

Data Index: 1624372 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1794742 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4152. Min Act: -0.0000

Data Index: 671085 (The Pile)

Max Activating Token Index: 279

Text #19

Max Range: 0.6894. Min Range: -0.6894

Max Act: 0.4000. Min Act: 0.0001

Data Index: 1225070 (The Pile)

Max Activating Token Index: 687