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

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

Neuron 1717 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.8675. Min Act: -0.0002

Data Index: 624616 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.6577. Min Act: -0.0002

Data Index: 552735 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.6043. Min Act: -0.0002

Data Index: 113089 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.4044. Min Act: -0.0002

Data Index: 337672 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.4665. Min Act: -0.0002

Data Index: 396080 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.3923. Min Act: -0.0002

Data Index: 1305716 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.3351. Min Act: -0.0002

Data Index: 461404 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.3306. Min Act: -0.0002

Data Index: 573035 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.3246. Min Act: -0.0002

Data Index: 189290 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.3173. Min Act: -0.0002

Data Index: 1016704 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.3133. Min Act: -0.0002

Data Index: 599245 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.3714. Min Act: -0.0002

Data Index: 30954 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.3347. Min Act: -0.0002

Data Index: 864604 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.2620. Min Act: -0.0002

Data Index: 49589 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.2500. Min Act: -0.0002

Data Index: 1320686 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.2522. Min Act: -0.0002

Data Index: 435067 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.2490. Min Act: -0.0002

Data Index: 1045691 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.2447. Min Act: -0.0002

Data Index: 298283 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.2232. Min Act: -0.0002

Data Index: 451403 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 13.8675. Min Range: -13.8675

Max Act: 13.2816. Min Act: -0.0002

Data Index: 139604 (C4 (Web Text))

Max Activating Token Index: 771