Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0420. Min Act: -0.0001

Data Index: 850053 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0448. Min Act: -0.0002

Data Index: 591006 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0451. Min Act: -0.0001

Data Index: 451824 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0415. Min Act: -0.0002

Data Index: 561096 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0396. Min Act: -0.0002

Data Index: 732446 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0443. Min Act: -0.0002

Data Index: 884654 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0442. Min Act: -0.0002

Data Index: 287039 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0430. Min Act: -0.0001

Data Index: 53661 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0453. Min Act: -0.0002

Data Index: 128268 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0373. Min Act: -0.0001

Data Index: 1270088 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0391. Min Act: -0.0001

Data Index: 1218497 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0423. Min Act: -0.0002

Data Index: 36638 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1017165 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0459. Min Act: -0.0002

Data Index: 913235 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1251854 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0420. Min Act: -0.0002

Data Index: 684356 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0386. Min Act: -0.0001

Data Index: 800650 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0436. Min Act: -0.0002

Data Index: 866314 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0403. Min Act: -0.0002

Data Index: 565737 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.0459. Min Range: -0.0459

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1168997 (C4 (Web Text))

Max Activating Token Index: 779