Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 64 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1390. Min Act: -0.0000

Data Index: 1073944 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1353. Min Act: -0.0000

Data Index: 235103 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1406. Min Act: -0.0000

Data Index: 447849 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1323. Min Act: -0.0000

Data Index: 513234 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1316. Min Act: -0.0000

Data Index: 278866 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1304. Min Act: -0.0000

Data Index: 529276 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1255. Min Act: -0.0000

Data Index: 924108 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1285945 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1300. Min Act: -0.0000

Data Index: 150435 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1222. Min Act: -0.0000

Data Index: 240493 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1281669 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1301944 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1200. Min Act: -0.0001

Data Index: 473203 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1222. Min Act: -0.0000

Data Index: 357380 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1177. Min Act: -0.0000

Data Index: 683827 (C4 (Web Text))

Max Activating Token Index: 335

Text #15

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1276961 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1198. Min Act: -0.0000

Data Index: 756553 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1148268 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1012141 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.1406. Min Range: -0.1406

Max Act: 0.1129. Min Act: -0.0000

Data Index: 379784 (C4 (Web Text))

Max Activating Token Index: 206