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

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

Neuron 5721 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3192. Min Range: -2.3192

Max Act: 2.3192. Min Act: -0.0001

Data Index: 723723 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 2.3192. Min Range: -2.3192

Max Act: 2.3115. Min Act: -0.0001

Data Index: 1176641 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 2.3192. Min Range: -2.3192

Max Act: 2.1598. Min Act: -0.0000

Data Index: 1257954 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 2.3192. Min Range: -2.3192

Max Act: 2.1336. Min Act: -0.0000

Data Index: 477676 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8379. Min Act: -0.0000

Data Index: 638047 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.9194. Min Act: -0.0001

Data Index: 350207 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8532. Min Act: -0.0000

Data Index: 716470 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.9695. Min Act: -0.0000

Data Index: 280713 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.7344. Min Act: -0.0001

Data Index: 212878 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.7243. Min Act: -0.0001

Data Index: 1214212 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8813. Min Act: -0.0000

Data Index: 851366 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.7739. Min Act: -0.0000

Data Index: 534321 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8364. Min Act: -0.0000

Data Index: 201129 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8946. Min Act: -0.0000

Data Index: 652798 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8777. Min Act: -0.0000

Data Index: 921641 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.7546. Min Act: -0.0000

Data Index: 442402 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.7346. Min Act: -0.0000

Data Index: 100636 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.6055. Min Act: -0.0000

Data Index: 979565 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.8551. Min Act: -0.0000

Data Index: 1156382 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 2.3192. Min Range: -2.3192

Max Act: 1.7293. Min Act: -0.0000

Data Index: 609307 (C4 (Web Text))

Max Activating Token Index: 188