Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1135 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1281500 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0405. Min Act: -0.0000

Data Index: 493491 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0000

Data Index: 512602 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0397. Min Act: -0.0000

Data Index: 328680 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0360. Min Act: -0.0000

Data Index: 226855 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0371. Min Act: -0.0000

Data Index: 62511 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0378. Min Act: -0.0000

Data Index: 69451 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0376. Min Act: -0.0000

Data Index: 1189133 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0357. Min Act: -0.0000

Data Index: 629918 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0351. Min Act: -0.0000

Data Index: 193645 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0353. Min Act: -0.0000

Data Index: 90047 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0339. Min Act: -0.0000

Data Index: 17868 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0349. Min Act: -0.0000

Data Index: 434330 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0347. Min Act: -0.0000

Data Index: 462071 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0339. Min Act: -0.0000

Data Index: 48817 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0324. Min Act: -0.0000

Data Index: 646074 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0325. Min Act: -0.0000

Data Index: 1147123 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0321. Min Act: -0.0000

Data Index: 629410 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1159049 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0303. Min Act: -0.0000

Data Index: 364789 (C4 (Web Text))

Max Activating Token Index: 967