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

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

Neuron 128 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3333. Min Range: -2.3333

Max Act: 2.3333. Min Act: -0.0000

Data Index: 627362 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.8999. Min Act: -0.0000

Data Index: 356062 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.9384. Min Act: -0.0000

Data Index: 856138 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.8117. Min Act: -0.0000

Data Index: 1061657 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.7381. Min Act: -0.0000

Data Index: 587899 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.7512. Min Act: -0.0000

Data Index: 511895 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.7276. Min Act: -0.0000

Data Index: 1135448 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4811. Min Act: -0.0000

Data Index: 890224 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4771. Min Act: -0.0000

Data Index: 834673 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1135231 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4385. Min Act: -0.0000

Data Index: 1129914 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4294. Min Act: -0.0000

Data Index: 15835 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4234. Min Act: -0.0000

Data Index: 546345 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1127122 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4299. Min Act: -0.0000

Data Index: 973263 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.3024. Min Act: -0.0000

Data Index: 468876 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.2863. Min Act: -0.0000

Data Index: 62132 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.3102. Min Act: -0.0000

Data Index: 460302 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.2909. Min Act: -0.0000

Data Index: 1243357 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.2529. Min Act: -0.0000

Data Index: 1247651 (C4 (Web Text))

Max Activating Token Index: 854