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

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

Neuron 3762 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: 0.1745. Min Range: -0.1745

Max Act: 0.1745. Min Act: -0.0001

Data Index: 695205 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1391699 (Python Code)

Max Activating Token Index: 175

Text #2

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1468. Min Act: -0.0001

Data Index: 701926 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1288082 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1202. Min Act: -0.0001

Data Index: 1321661 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1334. Min Act: -0.0001

Data Index: 612222 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1260. Min Act: -0.0001

Data Index: 597229 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1330. Min Act: -0.0001

Data Index: 99957 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1296489 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1466723 (Python Code)

Max Activating Token Index: 332

Text #10

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1322. Min Act: -0.0001

Data Index: 972617 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1522746 (Python Code)

Max Activating Token Index: 656

Text #12

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1246. Min Act: -0.0002

Data Index: 661966 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1502000 (Python Code)

Max Activating Token Index: 1012

Text #14

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1270. Min Act: -0.0001

Data Index: 343595 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1279315 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1299. Min Act: -0.0001

Data Index: 234129 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1211. Min Act: -0.0001

Data Index: 485133 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1338996 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.1745. Min Range: -0.1745

Max Act: 0.1190. Min Act: -0.0001

Data Index: 261906 (C4 (Web Text))

Max Activating Token Index: 146