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

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

Neuron 2117 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0242. Min Act: -0.0004

Data Index: 998772 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0218. Min Act: -0.0003

Data Index: 353853 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1179694 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0211. Min Act: -0.0004

Data Index: 226037 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0219. Min Act: -0.0003

Data Index: 261174 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0215. Min Act: -0.0003

Data Index: 53236 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0213. Min Act: -0.0004

Data Index: 461894 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0206. Min Act: -0.0004

Data Index: 607336 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0203. Min Act: -0.0003

Data Index: 370591 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0202. Min Act: -0.0004

Data Index: 1184888 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0202. Min Act: -0.0004

Data Index: 785442 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1339406 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0201. Min Act: -0.0004

Data Index: 1218318 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0202. Min Act: -0.0004

Data Index: 1015291 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0197. Min Act: -0.0003

Data Index: 949114 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0196. Min Act: -0.0004

Data Index: 823621 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0191. Min Act: -0.0003

Data Index: 426451 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0194. Min Act: -0.0003

Data Index: 1185915 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0193. Min Act: -0.0003

Data Index: 342501 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0242. Min Range: -0.0242

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1099419 (C4 (Web Text))

Max Activating Token Index: 632