Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3583 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1321032 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1834. Min Act: -0.0000

Data Index: 439194 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1600. Min Act: -0.0000

Data Index: 982555 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1484. Min Act: -0.0000

Data Index: 707730 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1514. Min Act: -0.0000

Data Index: 688207 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1271296 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1285108 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1433. Min Act: -0.0000

Data Index: 333259 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1519. Min Act: -0.0000

Data Index: 907196 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1214212 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1022299 (C4 (Web Text))

Max Activating Token Index: 189

Text #11

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1330. Min Act: -0.0000

Data Index: 26127 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1300477 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1336. Min Act: -0.0000

Data Index: 469182 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1334. Min Act: -0.0000

Data Index: 19894 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1254137 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1364. Min Act: -0.0000

Data Index: 678726 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1074250 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1293. Min Act: -0.0000

Data Index: 459524 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.1834. Min Range: -0.1834

Max Act: 0.1091. Min Act: -0.0000

Data Index: 606702 (C4 (Web Text))

Max Activating Token Index: 900