Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2906 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0252. Min Act: -0.0004

Data Index: 1456437 (Python Code)

Max Activating Token Index: 371

Text #1

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0232. Min Act: -0.0004

Data Index: 1654898 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1243363 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0004

Data Index: 1536699 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0224. Min Act: -0.0004

Data Index: 1541253 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0213. Min Act: -0.0004

Data Index: 1483163 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1474780 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0214. Min Act: -0.0004

Data Index: 610856 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0213. Min Act: -0.0004

Data Index: 1470255 (Python Code)

Max Activating Token Index: 629

Text #9

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1360670 (Python Code)

Max Activating Token Index: 445

Text #10

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0199. Min Act: -0.0004

Data Index: 1415542 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0228. Min Act: -0.0004

Data Index: 327475 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0205. Min Act: -0.0004

Data Index: 1392320 (Python Code)

Max Activating Token Index: 72

Text #13

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0202. Min Act: -0.0004

Data Index: 359654 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0207. Min Act: -0.0004

Data Index: 645670 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1587988 (Python Code)

Max Activating Token Index: 1002

Text #16

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1366971 (Python Code)

Max Activating Token Index: 321

Text #17

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1597362 (Python Code)

Max Activating Token Index: 70

Text #18

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0198. Min Act: -0.0004

Data Index: 1410232 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 0.0252. Min Range: -0.0252

Max Act: 0.0193. Min Act: -0.0004

Data Index: 1011506 (C4 (Web Text))

Max Activating Token Index: 182