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

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

Neuron 2553 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0463. Min Act: -0.0001

Data Index: 1090250 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0392. Min Act: -0.0001

Data Index: 954808 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1018205 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0418. Min Act: -0.0000

Data Index: 703629 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0385. Min Act: -0.0000

Data Index: 522247 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0392. Min Act: -0.0001

Data Index: 1257528 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0327. Min Act: -0.0000

Data Index: 145773 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1219855 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1036631 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0363. Min Act: -0.0000

Data Index: 233006 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0346. Min Act: -0.0000

Data Index: 998441 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0317. Min Act: -0.0000

Data Index: 687791 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0393. Min Act: -0.0000

Data Index: 25623 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0342. Min Act: -0.0000

Data Index: 460461 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0394. Min Act: -0.0000

Data Index: 895758 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0331. Min Act: -0.0001

Data Index: 21131 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0350. Min Act: -0.0000

Data Index: 68981 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1620113 (Python Code)

Max Activating Token Index: 679

Text #18

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0326. Min Act: -0.0001

Data Index: 107372 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 0.0463. Min Range: -0.0463

Max Act: 0.0371. Min Act: -0.0000

Data Index: 885191 (C4 (Web Text))

Max Activating Token Index: 855