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

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

Neuron 2700 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: 6.3509. Min Range: -6.3509

Max Act: 5.9130. Min Act: -0.0000

Data Index: 1108356 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 6.3509. Min Range: -6.3509

Max Act: 6.0279. Min Act: -0.0000

Data Index: 219396 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 6.3509. Min Range: -6.3509

Max Act: 6.3509. Min Act: -0.0000

Data Index: 1253505 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.8546. Min Act: -0.0000

Data Index: 807562 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.4742. Min Act: -0.0000

Data Index: 302720 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.7546. Min Act: -0.0000

Data Index: 561166 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.4631. Min Act: -0.0000

Data Index: 498862 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.7693. Min Act: -0.0000

Data Index: 122896 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.4112. Min Act: -0.0000

Data Index: 337290 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.5328. Min Act: -0.0000

Data Index: 1043747 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.3301. Min Act: -0.0000

Data Index: 435323 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.3436. Min Act: -0.0000

Data Index: 386288 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.4629. Min Act: -0.0000

Data Index: 802152 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.2588. Min Act: -0.0000

Data Index: 1273123 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.1025. Min Act: -0.0000

Data Index: 21826 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 6.3509. Min Range: -6.3509

Max Act: 5.0306. Min Act: -0.0000

Data Index: 939539 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 6.3509. Min Range: -6.3509

Max Act: 4.9188. Min Act: -0.0000

Data Index: 1288241 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 6.3509. Min Range: -6.3509

Max Act: 4.8604. Min Act: -0.0000

Data Index: 480191 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 6.3509. Min Range: -6.3509

Max Act: 4.6843. Min Act: -0.0000

Data Index: 1217539 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 6.3509. Min Range: -6.3509

Max Act: 4.8373. Min Act: -0.0000

Data Index: 392591 (C4 (Web Text))

Max Activating Token Index: 879