Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3243 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0300. Min Range: -1.0300

Max Act: 1.0300. Min Act: -0.0001

Data Index: 18354 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.9154. Min Act: -0.0000

Data Index: 20904 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8772. Min Act: -0.0001

Data Index: 27659 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8432. Min Act: -0.0001

Data Index: 1147897 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8376. Min Act: -0.0001

Data Index: 313069 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8609. Min Act: -0.0001

Data Index: 807962 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8867. Min Act: -0.0001

Data Index: 39154 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1155630 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8553. Min Act: -0.0000

Data Index: 700063 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8568. Min Act: -0.0000

Data Index: 595395 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8270. Min Act: -0.0000

Data Index: 1099298 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8282. Min Act: -0.0000

Data Index: 313836 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8382. Min Act: -0.0001

Data Index: 34535 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8376. Min Act: -0.0000

Data Index: 948353 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.7708. Min Act: -0.0000

Data Index: 43868 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1262375 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1051654 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8001. Min Act: -0.0000

Data Index: 865464 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8247. Min Act: -0.0000

Data Index: 445643 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8045. Min Act: -0.0000

Data Index: 127003 (C4 (Web Text))

Max Activating Token Index: 194