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

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

Neuron 981 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1382182 (Python Code)

Max Activating Token Index: 511

Text #1

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9973. Min Act: -0.0000

Data Index: 388705 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1363912 (Python Code)

Max Activating Token Index: 856

Text #3

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9601. Min Act: -0.0000

Data Index: 807854 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1379818 (Python Code)

Max Activating Token Index: 459

Text #5

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1281380 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9319. Min Act: -0.0000

Data Index: 403183 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9180. Min Act: -0.0000

Data Index: 423048 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8625. Min Act: -0.0000

Data Index: 523304 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8829. Min Act: -0.0000

Data Index: 202320 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1192702 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8693. Min Act: -0.0000

Data Index: 459750 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1519919 (Python Code)

Max Activating Token Index: 523

Text #13

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1396826 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8054. Min Act: -0.0000

Data Index: 1177134 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8048. Min Act: -0.0000

Data Index: 316369 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.7891. Min Act: -0.0000

Data Index: 21522 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1194376 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.7468. Min Act: -0.0000

Data Index: 100200 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8460. Min Act: -0.0000

Data Index: 796477 (C4 (Web Text))

Max Activating Token Index: 452