Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1894 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0272. Min Act: -0.0006

Data Index: 1132294 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0237. Min Act: -0.0006

Data Index: 958206 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1535944 (Python Code)

Max Activating Token Index: 789

Text #3

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0234. Min Act: -0.0006

Data Index: 617979 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0238. Min Act: -0.0006

Data Index: 279256 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1300063 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0229. Min Act: -0.0006

Data Index: 773335 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0234. Min Act: -0.0006

Data Index: 561807 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1190091 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1581440 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0238. Min Act: -0.0006

Data Index: 1224526 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0231. Min Act: -0.0006

Data Index: 389373 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1275287 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0217. Min Act: -0.0006

Data Index: 474822 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0232. Min Act: -0.0006

Data Index: 106581 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0222. Min Act: -0.0006

Data Index: 463575 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0221. Min Act: -0.0006

Data Index: 912323 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0212. Min Act: -0.0006

Data Index: 371571 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0226. Min Act: -0.0006

Data Index: 1424554 (Python Code)

Max Activating Token Index: 956

Text #19

Max Range: 0.0272. Min Range: -0.0272

Max Act: 0.0219. Min Act: -0.0006

Data Index: 769013 (C4 (Web Text))

Max Activating Token Index: 809