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

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

Neuron 2377 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: 0.0473. Min Range: -0.0473

Max Act: 0.0473. Min Act: -0.0001

Data Index: 912150 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0465. Min Act: -0.0001

Data Index: 582679 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1260572 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1602988 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0422. Min Act: -0.0001

Data Index: 740520 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0388. Min Act: -0.0001

Data Index: 758715 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0377. Min Act: -0.0001

Data Index: 508453 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0390. Min Act: -0.0001

Data Index: 250987 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1453625 (Python Code)

Max Activating Token Index: 759

Text #9

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1490105 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0344. Min Act: -0.0001

Data Index: 182256 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1213920 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0319. Min Act: -0.0001

Data Index: 1209947 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1157379 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1465999 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0315. Min Act: -0.0001

Data Index: 586927 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0298. Min Act: -0.0001

Data Index: 283718 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1392209 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1603199 (Python Code)

Max Activating Token Index: 704

Text #19

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1261353 (C4 (Web Text))

Max Activating Token Index: 304