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

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

Neuron 629 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: 0.2302. Min Range: -0.2302

Max Act: 0.2302. Min Act: -0.0000

Data Index: 963013 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1234605 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1214649 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1450. Min Act: -0.0000

Data Index: 402702 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1320635 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1288602 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1475. Min Act: -0.0000

Data Index: 370462 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1635. Min Act: -0.0000

Data Index: 643943 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1477. Min Act: -0.0000

Data Index: 662910 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1568. Min Act: -0.0000

Data Index: 768018 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1383. Min Act: -0.0000

Data Index: 569888 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1364. Min Act: -0.0000

Data Index: 778556 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1335. Min Act: -0.0000

Data Index: 176139 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1197385 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1242580 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1246. Min Act: -0.0000

Data Index: 823046 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1160790 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1221. Min Act: -0.0000

Data Index: 1217703 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1053. Min Act: -0.0000

Data Index: 805444 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.2302. Min Range: -0.2302

Max Act: 0.1099. Min Act: -0.0000

Data Index: 500795 (C4 (Web Text))

Max Activating Token Index: 691