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

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

Neuron 5020 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1507. Min Act: -0.0002

Data Index: 413102 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1490. Min Act: -0.0002

Data Index: 580023 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1474. Min Act: -0.0002

Data Index: 1240573 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1341. Min Act: -0.0002

Data Index: 944210 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1395. Min Act: -0.0002

Data Index: 251796 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1321. Min Act: -0.0002

Data Index: 286381 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1225. Min Act: -0.0002

Data Index: 350341 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1308. Min Act: -0.0002

Data Index: 1290528 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1514. Min Act: -0.0002

Data Index: 814800 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1239406 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1246. Min Act: -0.0002

Data Index: 811638 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1388. Min Act: -0.0002

Data Index: 73871 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1104171 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1283. Min Act: -0.0002

Data Index: 136360 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1353. Min Act: -0.0002

Data Index: 314432 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1280474 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1296. Min Act: -0.0002

Data Index: 540309 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1294. Min Act: -0.0002

Data Index: 826007 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1285388 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.1514. Min Range: -0.1514

Max Act: 0.1355. Min Act: -0.0002

Data Index: 625755 (C4 (Web Text))

Max Activating Token Index: 948