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

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

Neuron 4417 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0467. Min Act: -0.0002

Data Index: 686001 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0002

Data Index: 553694 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1020460 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0444. Min Act: -0.0002

Data Index: 660809 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0435. Min Act: -0.0002

Data Index: 603028 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0465. Min Act: -0.0002

Data Index: 1197961 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0408. Min Act: -0.0002

Data Index: 586748 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0439. Min Act: -0.0002

Data Index: 828894 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1295467 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1062201 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1333529 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1192770 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0426. Min Act: -0.0002

Data Index: 603395 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1141590 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0425. Min Act: -0.0002

Data Index: 811234 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1299430 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0423. Min Act: -0.0002

Data Index: 783911 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1343862 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0383. Min Act: -0.0002

Data Index: 461322 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0386. Min Act: -0.0002

Data Index: 408010 (C4 (Web Text))

Max Activating Token Index: 721