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

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

Neuron 2202 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: 0.4867. Min Range: -0.4867

Max Act: 0.4867. Min Act: -0.0000

Data Index: 436594 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1055633 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.4232. Min Act: -0.0000

Data Index: 979206 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3704. Min Act: -0.0000

Data Index: 1353811 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3659. Min Act: -0.0000

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3578. Min Act: -0.0000

Data Index: 317804 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3556. Min Act: -0.0000

Data Index: 1082435 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3789. Min Act: -0.0000

Data Index: 552395 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3382. Min Act: -0.0000

Data Index: 136123 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3442. Min Act: -0.0000

Data Index: 974833 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.2572. Min Act: -0.0000

Data Index: 545068 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3351. Min Act: -0.0000

Data Index: 536388 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3325. Min Act: -0.0000

Data Index: 912592 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3308. Min Act: -0.0000

Data Index: 182594 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3306. Min Act: -0.0000

Data Index: 285629 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3503. Min Act: -0.0000

Data Index: 637049 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3354. Min Act: -0.0000

Data Index: 249726 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3236. Min Act: -0.0000

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.4867. Min Range: -0.4867

Max Act: 0.3440. Min Act: -0.0000

Data Index: 283753 (C4 (Web Text))

Max Activating Token Index: 236