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

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

Neuron 2132 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0002

Data Index: 266687 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0280. Min Act: -0.0002

Data Index: 4989 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0268. Min Act: -0.0002

Data Index: 51428 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0265. Min Act: -0.0002

Data Index: 45290 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1139488 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0251. Min Act: -0.0002

Data Index: 350908 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0249. Min Act: -0.0002

Data Index: 74955 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0247. Min Act: -0.0002

Data Index: 251925 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0248. Min Act: -0.0002

Data Index: 849345 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0232. Min Act: -0.0002

Data Index: 680036 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0235. Min Act: -0.0002

Data Index: 46244 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0237. Min Act: -0.0002

Data Index: 981161 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1263327 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0235. Min Act: -0.0002

Data Index: 254811 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0231. Min Act: -0.0002

Data Index: 604583 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1194481 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1051048 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0234. Min Act: -0.0002

Data Index: 895307 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0235. Min Act: -0.0002

Data Index: 479017 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0239. Min Act: -0.0002

Data Index: 58303 (C4 (Web Text))

Max Activating Token Index: 667