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

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

Neuron 3403 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: 1.0472. Min Range: -1.0472

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1202031 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 1.0472. Min Range: -1.0472

Max Act: 1.0374. Min Act: -0.0000

Data Index: 1265709 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 1.0472. Min Range: -1.0472

Max Act: 1.0097. Min Act: -0.0000

Data Index: 69639 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8426. Min Act: -0.0000

Data Index: 36894 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8335. Min Act: -0.0000

Data Index: 655993 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1254844 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1284936 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8801. Min Act: -0.0000

Data Index: 1139639 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8015. Min Act: -0.0000

Data Index: 246786 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8742. Min Act: -0.0000

Data Index: 519384 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8116. Min Act: 0.0001

Data Index: 1188460 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1271651 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8021. Min Act: -0.0000

Data Index: 233425 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8035. Min Act: -0.0000

Data Index: 744552 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7725. Min Act: -0.0000

Data Index: 961635 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7449. Min Act: -0.0000

Data Index: 500900 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7526. Min Act: -0.0000

Data Index: 220570 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7244. Min Act: -0.0000

Data Index: 31548 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7210. Min Act: -0.0000

Data Index: 835423 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.6565. Min Act: -0.0000

Data Index: 907104 (C4 (Web Text))

Max Activating Token Index: 925