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

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

Neuron 2538 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: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0004

Data Index: 709233 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0272. Min Act: -0.0004

Data Index: 1278408 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0287. Min Act: -0.0004

Data Index: 957916 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0276. Min Act: -0.0004

Data Index: 240561 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0253. Min Act: -0.0004

Data Index: 1228329 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0269. Min Act: -0.0004

Data Index: 813090 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0231. Min Act: -0.0004

Data Index: 376526 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0266. Min Act: -0.0004

Data Index: 305209 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0265. Min Act: -0.0004

Data Index: 395203 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0234. Min Act: -0.0004

Data Index: 63339 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0274. Min Act: -0.0004

Data Index: 545493 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0241. Min Act: -0.0004

Data Index: 958331 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0281. Min Act: -0.0004

Data Index: 623258 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0237. Min Act: -0.0004

Data Index: 822027 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0227. Min Act: -0.0004

Data Index: 681994 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0232. Min Act: -0.0004

Data Index: 120940 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0221. Min Act: -0.0004

Data Index: 397703 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0269. Min Act: -0.0004

Data Index: 1104466 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0248. Min Act: -0.0004

Data Index: 432373 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1239298 (C4 (Web Text))

Max Activating Token Index: 700