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

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

Neuron 280 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1625. Min Act: -0.0001

Data Index: 936209 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1567. Min Act: 0.0001

Data Index: 1204525 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1532. Min Act: -0.0001

Data Index: 10087 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1496. Min Act: -0.0001

Data Index: 225028 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1423. Min Act: -0.0001

Data Index: 703961 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1409. Min Act: 0.0002

Data Index: 1011354 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1367. Min Act: -0.0001

Data Index: 466624 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1129269 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1373. Min Act: 0.0001

Data Index: 518349 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1391. Min Act: 0.0002

Data Index: 193809 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1306. Min Act: -0.0001

Data Index: 568631 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1346. Min Act: -0.0001

Data Index: 981078 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1326. Min Act: 0.0004

Data Index: 357339 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1371. Min Act: -0.0001

Data Index: 287170 (C4 (Web Text))

Max Activating Token Index: 251

Text #14

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1308. Min Act: -0.0000

Data Index: 840576 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1317. Min Act: 0.0001

Data Index: 1276677 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1304. Min Act: -0.0001

Data Index: 863815 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1339. Min Act: -0.0001

Data Index: 1206971 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1331. Min Act: -0.0000

Data Index: 1348654 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.1625. Min Range: -0.1625

Max Act: 0.1292. Min Act: -0.0001

Data Index: 319769 (C4 (Web Text))

Max Activating Token Index: 187