Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 391 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0408. Min Act: -0.0003

Data Index: 1307992 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0409. Min Act: -0.0003

Data Index: 134248 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1150692 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0383. Min Act: -0.0003

Data Index: 734863 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0396. Min Act: -0.0003

Data Index: 497219 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0397. Min Act: -0.0003

Data Index: 29893 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0004

Data Index: 1029952 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0374. Min Act: -0.0003

Data Index: 482704 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0389. Min Act: -0.0003

Data Index: 340258 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0379. Min Act: -0.0003

Data Index: 796497 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1008469 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0380. Min Act: -0.0003

Data Index: 462329 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0372. Min Act: -0.0003

Data Index: 968909 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0360. Min Act: -0.0003

Data Index: 617948 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1184258 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0372. Min Act: -0.0004

Data Index: 740253 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0371. Min Act: -0.0002

Data Index: 858031 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0373. Min Act: -0.0003

Data Index: 775575 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0390. Min Act: -0.0004

Data Index: 976079 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0370. Min Act: -0.0003

Data Index: 400029 (C4 (Web Text))

Max Activating Token Index: 248