Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3885 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1432097 (Python Code)

Max Activating Token Index: 842

Text #1

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0221. Min Act: -0.0003

Data Index: 492279 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0224. Min Act: -0.0003

Data Index: 522581 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1250669 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0190. Min Act: -0.0003

Data Index: 960355 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0205. Min Act: -0.0004

Data Index: 1158808 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0215. Min Act: -0.0003

Data Index: 370647 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1516479 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0208. Min Act: -0.0003

Data Index: 443987 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1171405 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0215. Min Act: -0.0004

Data Index: 345400 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0211. Min Act: -0.0003

Data Index: 112378 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0213. Min Act: -0.0003

Data Index: 859682 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0218. Min Act: -0.0003

Data Index: 913714 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0205. Min Act: -0.0003

Data Index: 86222 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1492702 (Python Code)

Max Activating Token Index: 374

Text #16

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1107349 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0215. Min Act: -0.0003

Data Index: 809488 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0224. Min Act: -0.0003

Data Index: 254397 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0263. Min Range: -0.0263

Max Act: 0.0206. Min Act: -0.0003

Data Index: 2477 (C4 (Web Text))

Max Activating Token Index: 38