Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1586 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1221977 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1292708 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1256178 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1213583 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1339. Min Act: -0.0000

Data Index: 887537 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1365. Min Act: -0.0001

Data Index: 681466 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1315. Min Act: -0.0001

Data Index: 412093 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1282. Min Act: -0.0000

Data Index: 317995 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1282. Min Act: -0.0000

Data Index: 1259921 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1281. Min Act: -0.0001

Data Index: 918304 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1269. Min Act: -0.0000

Data Index: 431239 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1337493 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1252. Min Act: -0.0000

Data Index: 847152 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1098076 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1288. Min Act: -0.0001

Data Index: 27719 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1212. Min Act: -0.0000

Data Index: 911920 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1203. Min Act: -0.0000

Data Index: 391768 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1244. Min Act: -0.0001

Data Index: 397711 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1215. Min Act: -0.0001

Data Index: 314345 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.1506. Min Range: -0.1506

Max Act: 0.1092. Min Act: -0.0001

Data Index: 276907 (C4 (Web Text))

Max Activating Token Index: 113