Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1635 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1812. Min Act: 0.0000

Data Index: 716463 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1521. Min Act: -0.0000

Data Index: 216086 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1521. Min Act: -0.0000

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1534. Min Act: -0.0000

Data Index: 73902 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1434. Min Act: -0.0000

Data Index: 928808 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1355. Min Act: -0.0000

Data Index: 715928 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1438. Min Act: 0.0000

Data Index: 409319 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1417. Min Act: -0.0000

Data Index: 742637 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1305. Min Act: -0.0000

Data Index: 531716 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1409. Min Act: -0.0000

Data Index: 200726 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1271. Min Act: -0.0000

Data Index: 956392 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1157116 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1243. Min Act: -0.0000

Data Index: 316950 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1208. Min Act: -0.0000

Data Index: 477952 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1316688 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1228. Min Act: -0.0000

Data Index: 890376 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1213. Min Act: 0.0001

Data Index: 1283768 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1179. Min Act: -0.0000

Data Index: 741358 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1149. Min Act: -0.0000

Data Index: 65876 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.1812. Min Range: -0.1812

Max Act: 0.1168. Min Act: -0.0000

Data Index: 37917 (C4 (Web Text))

Max Activating Token Index: 36