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

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

Neuron 33 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: 0.0589. Min Range: -0.0589

Max Act: 0.0589. Min Act: -0.0001

Data Index: 421216 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0475. Min Act: -0.0001

Data Index: 810691 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0481. Min Act: -0.0001

Data Index: 331160 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0434. Min Act: -0.0001

Data Index: 600026 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0420. Min Act: -0.0001

Data Index: 3713 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0432. Min Act: -0.0000

Data Index: 546981 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0427. Min Act: -0.0001

Data Index: 189458 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0403. Min Act: -0.0001

Data Index: 487356 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0418. Min Act: -0.0001

Data Index: 557172 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0387. Min Act: -0.0001

Data Index: 1186862 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1290739 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0379. Min Act: -0.0001

Data Index: 860011 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0375. Min Act: -0.0001

Data Index: 746226 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0360. Min Act: -0.0000

Data Index: 484933 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1108604 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1325420 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0374. Min Act: -0.0001

Data Index: 234850 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0356. Min Act: -0.0001

Data Index: 250705 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0348. Min Act: -0.0001

Data Index: 371209 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.0589. Min Range: -0.0589

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1015734 (C4 (Web Text))

Max Activating Token Index: 572