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

Dataset: The Pile

Neuron 2328 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: 1.3005. Min Range: -1.3005

Max Act: 1.3005. Min Act: -0.0000

Data Index: 121164 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1897828 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.1057. Min Act: 0.0000

Data Index: 199617 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0849. Min Act: -0.0000

Data Index: 317663 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1515994 (The Pile)

Max Activating Token Index: 367

Text #5

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0624. Min Act: 0.0000

Data Index: 1982507 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 1.3005. Min Range: -1.3005

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1126647 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1245550 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9191. Min Act: 0.0001

Data Index: 429587 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1039069 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9623. Min Act: -0.0000

Data Index: 27943 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.8858. Min Act: 0.0000

Data Index: 220912 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9174. Min Act: -0.0000

Data Index: 877397 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9114. Min Act: -0.0000

Data Index: 1455626 (The Pile)

Max Activating Token Index: 287

Text #14

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.9009. Min Act: 0.0000

Data Index: 655666 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.8865. Min Act: -0.0000

Data Index: 255647 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1356246 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1896558 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.7872. Min Act: 0.0000

Data Index: 1547932 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 1.3005. Min Range: -1.3005

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1012004 (The Pile)

Max Activating Token Index: 281