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

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

Neuron 4347 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0000

Data Index: 646244 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0321. Min Act: -0.0000

Data Index: 53265 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0284. Min Act: -0.0000

Data Index: 401611 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0310. Min Act: -0.0000

Data Index: 463629 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0299. Min Act: -0.0000

Data Index: 347800 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0310. Min Act: -0.0000

Data Index: 227055 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1429045 (Python Code)

Max Activating Token Index: 357

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0286. Min Act: -0.0000

Data Index: 852463 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0291. Min Act: -0.0000

Data Index: 1083583 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0279. Min Act: -0.0000

Data Index: 171474 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0278. Min Act: -0.0000

Data Index: 796313 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0278. Min Act: -0.0000

Data Index: 190606 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0241. Min Act: -0.0000

Data Index: 1373528 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0250. Min Act: -0.0000

Data Index: 1418490 (Python Code)

Max Activating Token Index: 326

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0259. Min Act: -0.0000

Data Index: 197836 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0257. Min Act: -0.0000

Data Index: 275060 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1199641 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0266. Min Act: -0.0000

Data Index: 554184 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0262. Min Act: -0.0000

Data Index: 1080653 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0226. Min Act: -0.0000

Data Index: 109660 (C4 (Web Text))

Max Activating Token Index: 686