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

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

Neuron 638 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: 0.0436. Min Range: -0.0436

Max Act: 0.0436. Min Act: -0.0003

Data Index: 697669 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1050570 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0409. Min Act: -0.0003

Data Index: 335693 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0405. Min Act: -0.0002

Data Index: 716981 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0398. Min Act: -0.0003

Data Index: 974204 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1007110 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1077143 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0376. Min Act: -0.0002

Data Index: 763491 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1198721 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0373. Min Act: -0.0003

Data Index: 750910 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1143192 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0371. Min Act: -0.0003

Data Index: 757255 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0377. Min Act: -0.0003

Data Index: 361910 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0374. Min Act: -0.0002

Data Index: 224836 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0363. Min Act: -0.0003

Data Index: 277844 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0370. Min Act: -0.0003

Data Index: 561627 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0367. Min Act: -0.0003

Data Index: 831998 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0359. Min Act: -0.0002

Data Index: 69457 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0351. Min Act: -0.0002

Data Index: 56244 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 0.0436. Min Range: -0.0436

Max Act: 0.0358. Min Act: -0.0002

Data Index: 443592 (C4 (Web Text))

Max Activating Token Index: 527