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

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

Neuron 3500 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1027732 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.7164. Min Act: -0.0000

Data Index: 484266 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.7074. Min Act: -0.0000

Data Index: 372602 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1174561 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.6546. Min Act: -0.0000

Data Index: 206691 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.6352. Min Act: -0.0000

Data Index: 1202536 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.5873. Min Act: -0.0000

Data Index: 779 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.5838. Min Act: -0.0000

Data Index: 678109 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.5445. Min Act: -0.0000

Data Index: 651088 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1036241 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.5363. Min Act: -0.0000

Data Index: 811260 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.5172. Min Act: -0.0000

Data Index: 512623 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.4700. Min Act: -0.0000

Data Index: 201923 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.4790. Min Act: -0.0000

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.4532. Min Act: -0.0000

Data Index: 686790 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1094547 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.4182. Min Act: -0.0000

Data Index: 309274 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.4248. Min Act: -0.0000

Data Index: 188926 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.7319. Min Range: -0.7319

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1204185 (C4 (Web Text))

Max Activating Token Index: 588