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

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

Neuron 3672 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.7227. Min Act: -0.0000

Data Index: 497658 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.6127. Min Act: -0.0000

Data Index: 293564 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.7651. Min Act: -0.0000

Data Index: 1156089 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.5828. Min Act: -0.0000

Data Index: 1224929 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.5438. Min Act: -0.0000

Data Index: 571512 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.1579. Min Act: -0.0000

Data Index: 460733 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.2295. Min Act: -0.0000

Data Index: 999247 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.2282. Min Act: -0.0000

Data Index: 1304867 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.3251. Min Act: -0.0000

Data Index: 1305399 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.2223. Min Act: -0.0000

Data Index: 190077 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.2163. Min Act: -0.0000

Data Index: 756526 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.0700. Min Act: -0.0000

Data Index: 792496 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.2323. Min Act: -0.0000

Data Index: 1140419 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 5.7651. Min Range: -5.7651

Max Act: 4.9668. Min Act: -0.0000

Data Index: 1063387 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 5.7651. Min Range: -5.7651

Max Act: 5.1317. Min Act: -0.0000

Data Index: 990512 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 5.7651. Min Range: -5.7651

Max Act: 4.8365. Min Act: -0.0000

Data Index: 516286 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 5.7651. Min Range: -5.7651

Max Act: 4.9978. Min Act: -0.0000

Data Index: 395068 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 5.7651. Min Range: -5.7651

Max Act: 4.9431. Min Act: -0.0000

Data Index: 827418 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 5.7651. Min Range: -5.7651

Max Act: 4.9334. Min Act: -0.0000

Data Index: 706976 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 5.7651. Min Range: -5.7651

Max Act: 4.5806. Min Act: -0.0000

Data Index: 321949 (C4 (Web Text))

Max Activating Token Index: 551