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

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

Neuron 2229 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.6680. Min Act: -0.0000

Data Index: 30389 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.8992. Min Act: -0.0000

Data Index: 133359 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.8510. Min Act: -0.0000

Data Index: 1327312 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.7110. Min Act: -0.0000

Data Index: 583345 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.8334. Min Act: -0.0000

Data Index: 429382 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.6638. Min Act: -0.0000

Data Index: 273445 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.7568. Min Act: -0.0000

Data Index: 177157 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.3488. Min Act: -0.0000

Data Index: 127697 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.5981. Min Act: -0.0000

Data Index: 163971 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.7502. Min Act: -0.0000

Data Index: 502602 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.4719. Min Act: -0.0000

Data Index: 60243 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.8519. Min Act: -0.0000

Data Index: 655756 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.5683. Min Act: -0.0000

Data Index: 892392 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.8380. Min Act: -0.0000

Data Index: 530381 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.3746. Min Act: -0.0000

Data Index: 270183 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.3551. Min Act: -0.0000

Data Index: 380309 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.1279. Min Act: -0.0000

Data Index: 331910 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.2024. Min Act: -0.0000

Data Index: 326608 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.1852. Min Act: -0.0000

Data Index: 213121 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 2.8992. Min Range: -2.8992

Max Act: 2.2881. Min Act: -0.0000

Data Index: 119395 (C4 (Web Text))

Max Activating Token Index: 323