Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 625 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0241. Min Act: -0.0003

Data Index: 239861 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0218. Min Act: -0.0003

Data Index: 489455 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1256852 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0208. Min Act: -0.0003

Data Index: 714960 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0200. Min Act: -0.0002

Data Index: 856089 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1224462 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0202. Min Act: -0.0003

Data Index: 152 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0215. Min Act: -0.0003

Data Index: 652904 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0211. Min Act: -0.0002

Data Index: 768388 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1270019 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0186. Min Act: -0.0002

Data Index: 230646 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0177. Min Act: -0.0003

Data Index: 703729 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0193. Min Act: -0.0002

Data Index: 563597 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0201. Min Act: -0.0003

Data Index: 1053417 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0196. Min Act: -0.0002

Data Index: 445475 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0180. Min Act: -0.0003

Data Index: 897834 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0187. Min Act: -0.0002

Data Index: 562341 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1348480 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0193. Min Act: -0.0003

Data Index: 734934 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.0241. Min Range: -0.0241

Max Act: 0.0191. Min Act: -0.0003

Data Index: 820351 (C4 (Web Text))

Max Activating Token Index: 881