Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 15 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0300. Min Act: -0.0004

Data Index: 885417 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0297. Min Act: -0.0004

Data Index: 1051191 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0293. Min Act: -0.0002

Data Index: 177622 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0268. Min Act: -0.0004

Data Index: 1136232 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0276. Min Act: -0.0004

Data Index: 172738 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0257. Min Act: -0.0004

Data Index: 813552 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0263. Min Act: -0.0004

Data Index: 840422 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0251. Min Act: -0.0004

Data Index: 1075034 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0250. Min Act: -0.0004

Data Index: 206754 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0244. Min Act: -0.0004

Data Index: 909758 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1077569 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0239. Min Act: -0.0004

Data Index: 576928 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0226. Min Act: -0.0004

Data Index: 454215 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0226. Min Act: -0.0004

Data Index: 194030 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0222. Min Act: -0.0004

Data Index: 1283715 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1265594 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1588562 (Python Code)

Max Activating Token Index: 524

Text #17

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0217. Min Act: -0.0004

Data Index: 16391 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1267215 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.0300. Min Range: -0.0300

Max Act: 0.0218. Min Act: -0.0004

Data Index: 717416 (C4 (Web Text))

Max Activating Token Index: 68