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

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

Neuron 3073 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1695. Min Act: -0.0000

Data Index: 418903 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1131413 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1753. Min Act: -0.0000

Data Index: 234617 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1110113 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1426. Min Act: -0.0000

Data Index: 389988 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1378. Min Act: -0.0000

Data Index: 702014 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1171086 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1282. Min Act: -0.0000

Data Index: 529309 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1359. Min Act: -0.0000

Data Index: 106928 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1401. Min Act: -0.0000

Data Index: 119242 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1354811 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1164777 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1291. Min Act: -0.0000

Data Index: 36537 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1262. Min Act: -0.0000

Data Index: 326908 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1171079 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1230. Min Act: -0.0000

Data Index: 273648 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1197. Min Act: -0.0000

Data Index: 424286 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1337609 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1224. Min Act: -0.0000

Data Index: 714322 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1180. Min Act: -0.0000

Data Index: 331332 (C4 (Web Text))

Max Activating Token Index: 772