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

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

Neuron 3799 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1574. Min Act: -0.0001

Data Index: 982297 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1193644 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1106546 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1403. Min Act: -0.0001

Data Index: 678166 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1414. Min Act: -0.0001

Data Index: 186369 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1364. Min Act: -0.0001

Data Index: 213841 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1217960 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1203723 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1186428 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1311. Min Act: -0.0001

Data Index: 689069 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1566. Min Act: -0.0001

Data Index: 940771 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1346. Min Act: -0.0001

Data Index: 163001 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1280. Min Act: -0.0001

Data Index: 16365 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1274. Min Act: -0.0001

Data Index: 546686 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1229. Min Act: -0.0001

Data Index: 940340 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1310. Min Act: -0.0001

Data Index: 700724 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1113686 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1240. Min Act: -0.0001

Data Index: 528518 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1300. Min Act: -0.0001

Data Index: 213197 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.1660. Min Range: -0.1660

Max Act: 0.1178. Min Act: -0.0001

Data Index: 863249 (C4 (Web Text))

Max Activating Token Index: 445