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

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

Neuron 4846 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: 0.4168. Min Range: -0.4168

Max Act: 0.4168. Min Act: -0.0000

Data Index: 307532 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.3631. Min Act: -0.0000

Data Index: 85799 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.3334. Min Act: -0.0000

Data Index: 853181 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.3643. Min Act: -0.0000

Data Index: 966316 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2774. Min Act: -0.0000

Data Index: 175192 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2756. Min Act: -0.0000

Data Index: 310543 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2801. Min Act: -0.0000

Data Index: 97369 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2804. Min Act: -0.0000

Data Index: 369911 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2646. Min Act: -0.0000

Data Index: 678370 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2481. Min Act: -0.0000

Data Index: 255862 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2476. Min Act: -0.0000

Data Index: 845343 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2432. Min Act: -0.0000

Data Index: 597035 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2469. Min Act: -0.0000

Data Index: 751408 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2518. Min Act: -0.0000

Data Index: 914169 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1164663 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2242. Min Act: -0.0000

Data Index: 141167 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1107110 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1094605 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1099324 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 0.4168. Min Range: -0.4168

Max Act: 0.2126. Min Act: -0.0000

Data Index: 1081916 (C4 (Web Text))

Max Activating Token Index: 306