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

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

Neuron 1782 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1294427 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1244457 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4843. Min Act: -0.0000

Data Index: 103882 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4759. Min Act: -0.0000

Data Index: 415012 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4628. Min Act: -0.0000

Data Index: 877877 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4570. Min Act: -0.0000

Data Index: 517186 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4546. Min Act: 0.0000

Data Index: 748869 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1112277 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4248. Min Act: 0.0000

Data Index: 655324 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4639. Min Act: -0.0000

Data Index: 1222188 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4450. Min Act: -0.0000

Data Index: 769555 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4540. Min Act: -0.0000

Data Index: 712805 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4259. Min Act: -0.0000

Data Index: 389552 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4266. Min Act: -0.0000

Data Index: 229908 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1180601 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4383. Min Act: -0.0000

Data Index: 151137 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1079672 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4325. Min Act: -0.0000

Data Index: 468204 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4305. Min Act: -0.0000

Data Index: 11927 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.5349. Min Range: -0.5349

Max Act: 0.4129. Min Act: -0.0000

Data Index: 627337 (C4 (Web Text))

Max Activating Token Index: 738