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

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

Neuron 1110 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: 0.0472. Min Range: -0.0472

Max Act: 0.0464. Min Act: -0.0003

Data Index: 251473 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0003

Data Index: 380603 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0439. Min Act: -0.0003

Data Index: 60077 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0451. Min Act: -0.0003

Data Index: 361311 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0425. Min Act: -0.0003

Data Index: 58151 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0427. Min Act: -0.0003

Data Index: 886696 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1184874 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0387. Min Act: -0.0003

Data Index: 914852 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0399. Min Act: -0.0003

Data Index: 3928 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0403. Min Act: -0.0003

Data Index: 386645 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0394. Min Act: -0.0003

Data Index: 920837 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0383. Min Act: -0.0003

Data Index: 119080 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0383. Min Act: -0.0003

Data Index: 664973 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0379. Min Act: -0.0004

Data Index: 315537 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0388. Min Act: -0.0003

Data Index: 675444 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0378. Min Act: -0.0003

Data Index: 536652 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0379. Min Act: -0.0003

Data Index: 88916 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0387. Min Act: -0.0003

Data Index: 73170 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1092211 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1095034 (C4 (Web Text))

Max Activating Token Index: 506