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

Dataset: The Pile

Neuron 3171 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.0679. Min Range: -9.0679

Max Act: 9.0679. Min Act: -0.0000

Data Index: 406475 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 9.0679. Min Range: -9.0679

Max Act: 8.9185. Min Act: -0.0000

Data Index: 265727 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.9632. Min Act: -0.0000

Data Index: 272506 (The Pile)

Max Activating Token Index: 315

Text #3

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.8563. Min Act: -0.0000

Data Index: 475813 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.6607. Min Act: -0.0000

Data Index: 1223223 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.8596. Min Act: -0.0000

Data Index: 1079345 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.7566. Min Act: -0.0000

Data Index: 1342058 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.7847. Min Act: -0.0000

Data Index: 534010 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.0707. Min Act: -0.0000

Data Index: 903652 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.6275. Min Act: -0.0000

Data Index: 1388886 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.8087. Min Act: -0.0000

Data Index: 1522166 (The Pile)

Max Activating Token Index: 169

Text #11

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.7731. Min Act: -0.0000

Data Index: 262172 (The Pile)

Max Activating Token Index: 932

Text #12

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.3306. Min Act: -0.0000

Data Index: 1890278 (The Pile)

Max Activating Token Index: 324

Text #13

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.4335. Min Act: -0.0000

Data Index: 174948 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.2602. Min Act: -0.0000

Data Index: 1723135 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.4513. Min Act: -0.0000

Data Index: 1673624 (The Pile)

Max Activating Token Index: 347

Text #16

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.4309. Min Act: -0.0000

Data Index: 854066 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.4272. Min Act: -0.0000

Data Index: 1869945 (The Pile)

Max Activating Token Index: 379

Text #18

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.4346. Min Act: -0.0000

Data Index: 1708456 (The Pile)

Max Activating Token Index: 409

Text #19

Max Range: 9.0679. Min Range: -9.0679

Max Act: 7.3876. Min Act: -0.0000

Data Index: 539327 (The Pile)

Max Activating Token Index: 585