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

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

Neuron 4937 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1529385 (Python Code)

Max Activating Token Index: 938

Text #1

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0299. Min Act: -0.0002

Data Index: 282263 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0292. Min Act: -0.0002

Data Index: 129538 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0256. Min Act: -0.0002

Data Index: 966102 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1313629 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0267. Min Act: -0.0002

Data Index: 510161 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0249. Min Act: -0.0002

Data Index: 284292 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0229. Min Act: -0.0002

Data Index: 726163 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0223. Min Act: -0.0002

Data Index: 20933 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0223. Min Act: -0.0002

Data Index: 846073 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0221. Min Act: -0.0002

Data Index: 431000 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1283971 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0213. Min Act: -0.0002

Data Index: 846930 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0219. Min Act: -0.0002

Data Index: 672850 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0216. Min Act: -0.0002

Data Index: 1036504 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0224. Min Act: -0.0002

Data Index: 847227 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0213. Min Act: -0.0002

Data Index: 188152 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0216. Min Act: -0.0002

Data Index: 590141 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1040876 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.0377. Min Range: -0.0377

Max Act: 0.0206. Min Act: -0.0002

Data Index: 843955 (C4 (Web Text))

Max Activating Token Index: 421