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

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

Neuron 120 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1606. Min Act: -0.0001

Data Index: 21982 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1322575 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1383. Min Act: -0.0001

Data Index: 600349 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1469. Min Act: -0.0001

Data Index: 612685 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1260460 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1313. Min Act: -0.0001

Data Index: 595325 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1369. Min Act: -0.0001

Data Index: 1267074 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1411. Min Act: -0.0001

Data Index: 614649 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1332. Min Act: -0.0001

Data Index: 388792 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1143800 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1356. Min Act: -0.0001

Data Index: 895860 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1338. Min Act: -0.0001

Data Index: 662555 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1301. Min Act: -0.0001

Data Index: 276994 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1318646 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1321. Min Act: -0.0001

Data Index: 1250728 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1357. Min Act: -0.0001

Data Index: 988227 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1146. Min Act: -0.0001

Data Index: 702654 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1225. Min Act: -0.0001

Data Index: 434330 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1191. Min Act: -0.0001

Data Index: 1113017 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1185. Min Act: -0.0001

Data Index: 783499 (C4 (Web Text))

Max Activating Token Index: 633