Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1679 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1511. Min Act: -0.0003

Data Index: 695100 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1434. Min Act: -0.0003

Data Index: 697261 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1484. Min Act: -0.0003

Data Index: 161357 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1429. Min Act: -0.0003

Data Index: 285179 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1429. Min Act: -0.0003

Data Index: 214806 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1345. Min Act: -0.0003

Data Index: 1000455 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1231. Min Act: -0.0003

Data Index: 914898 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1396. Min Act: -0.0003

Data Index: 275314 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1341. Min Act: -0.0003

Data Index: 656493 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1473. Min Act: -0.0003

Data Index: 320047 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1386. Min Act: -0.0003

Data Index: 948012 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1243. Min Act: -0.0003

Data Index: 614668 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1313. Min Act: -0.0003

Data Index: 1010714 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1334. Min Act: -0.0003

Data Index: 651 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1344. Min Act: -0.0003

Data Index: 635144 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1284. Min Act: -0.0003

Data Index: 85883 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1319. Min Act: -0.0003

Data Index: 390809 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1301. Min Act: -0.0003

Data Index: 95358 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1393. Min Act: -0.0003

Data Index: 1088219 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1438. Min Act: -0.0003

Data Index: 973669 (C4 (Web Text))

Max Activating Token Index: 680