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

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

Neuron 2017 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1267542 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1372. Min Act: -0.0001

Data Index: 279375 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1346541 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1277. Min Act: -0.0001

Data Index: 483801 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1202. Min Act: -0.0001

Data Index: 777629 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1208. Min Act: -0.0002

Data Index: 74782 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1236. Min Act: -0.0001

Data Index: 402466 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1076829 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1334516 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1237. Min Act: -0.0001

Data Index: 731862 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1218. Min Act: -0.0001

Data Index: 560683 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1309. Min Act: -0.0001

Data Index: 992334 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1205. Min Act: -0.0001

Data Index: 817372 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1200. Min Act: -0.0001

Data Index: 350734 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1070. Min Act: -0.0001

Data Index: 640225 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1238. Min Act: -0.0001

Data Index: 672334 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1104. Min Act: -0.0001

Data Index: 973635 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1191. Min Act: -0.0001

Data Index: 142998 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1236. Min Act: -0.0001

Data Index: 245186 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.1471. Min Range: -0.1471

Max Act: 0.1062. Min Act: -0.0001

Data Index: 721732 (C4 (Web Text))

Max Activating Token Index: 740