Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5134 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5365. Min Range: -1.5365

Max Act: 1.5365. Min Act: -0.0000

Data Index: 636647 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.5365. Min Range: -1.5365

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1111203 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 1.5365. Min Range: -1.5365

Max Act: 1.0623. Min Act: -0.0000

Data Index: 448393 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.9656. Min Act: -0.0000

Data Index: 221086 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.9164. Min Act: -0.0000

Data Index: 457784 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.9006. Min Act: -0.0000

Data Index: 752425 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.8874. Min Act: -0.0000

Data Index: 832641 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.8616. Min Act: -0.0000

Data Index: 453364 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.9097. Min Act: -0.0000

Data Index: 469894 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.8666. Min Act: -0.0000

Data Index: 805036 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.8620. Min Act: -0.0000

Data Index: 473629 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.8039. Min Act: -0.0000

Data Index: 434653 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.8091. Min Act: -0.0000

Data Index: 896338 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.8010. Min Act: -0.0000

Data Index: 183391 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.7633. Min Act: -0.0000

Data Index: 203734 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1143849 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.7462. Min Act: -0.0000

Data Index: 4418 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.7389. Min Act: -0.0000

Data Index: 391300 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1304457 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 1.5365. Min Range: -1.5365

Max Act: 0.7169. Min Act: -0.0000

Data Index: 1197348 (C4 (Web Text))

Max Activating Token Index: 187