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

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

Neuron 1025 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: 0.0451. Min Range: -0.0451

Max Act: 0.0451. Min Act: -0.0002

Data Index: 652271 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1044916 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0441. Min Act: -0.0002

Data Index: 615328 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0428. Min Act: -0.0002

Data Index: 244844 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0408. Min Act: -0.0002

Data Index: 127973 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0396. Min Act: -0.0002

Data Index: 76895 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0382. Min Act: -0.0002

Data Index: 1043030 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1248494 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1032965 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1099528 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0396. Min Act: -0.0002

Data Index: 992660 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0415. Min Act: -0.0002

Data Index: 661763 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0380. Min Act: -0.0002

Data Index: 193550 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0383. Min Act: -0.0002

Data Index: 98856 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0398. Min Act: -0.0002

Data Index: 896745 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0388. Min Act: -0.0002

Data Index: 80634 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0372. Min Act: -0.0002

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0386. Min Act: -0.0002

Data Index: 953801 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0372. Min Act: -0.0002

Data Index: 976737 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.0451. Min Range: -0.0451

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1221653 (C4 (Web Text))

Max Activating Token Index: 274