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

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

Neuron 4281 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0266. Min Act: -0.0002

Data Index: 88757 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0239. Min Act: -0.0002

Data Index: 867071 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0236. Min Act: -0.0002

Data Index: 432262 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1347156 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1280563 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0227. Min Act: -0.0002

Data Index: 760079 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0225. Min Act: -0.0002

Data Index: 861338 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0223. Min Act: -0.0002

Data Index: 597238 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1350108 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0214. Min Act: -0.0002

Data Index: 456737 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0217. Min Act: -0.0002

Data Index: 738356 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0212. Min Act: -0.0002

Data Index: 994168 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0210. Min Act: -0.0002

Data Index: 541632 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0214. Min Act: -0.0002

Data Index: 447212 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0209. Min Act: -0.0002

Data Index: 627582 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0212. Min Act: -0.0002

Data Index: 43020 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0206. Min Act: -0.0002

Data Index: 738498 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0210. Min Act: -0.0002

Data Index: 297222 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1040277 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1063577 (C4 (Web Text))

Max Activating Token Index: 318