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

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

Neuron 3142 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.8606. Min Act: -0.0000

Data Index: 519398 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.7607. Min Act: -0.0000

Data Index: 1027479 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.3559. Min Act: -0.0000

Data Index: 258011 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.1554. Min Act: -0.0000

Data Index: 171455 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.1390. Min Act: -0.0000

Data Index: 984996 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.3672. Min Act: -0.0000

Data Index: 789017 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.2185. Min Act: -0.0000

Data Index: 809532 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.1588. Min Act: -0.0000

Data Index: 1245616 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.4209. Min Act: -0.0000

Data Index: 706868 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.9596. Min Act: -0.0000

Data Index: 81639 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.0517. Min Act: -0.0000

Data Index: 1154451 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 2.8606. Min Range: -2.8606

Max Act: 2.1236. Min Act: -0.0000

Data Index: 741889 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.9237. Min Act: -0.0000

Data Index: 872984 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.8384. Min Act: -0.0000

Data Index: 147341 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.9503. Min Act: -0.0000

Data Index: 62686 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.9387. Min Act: -0.0000

Data Index: 932018 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.9306. Min Act: -0.0000

Data Index: 137686 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.8135. Min Act: -0.0000

Data Index: 1174514 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.9945. Min Act: -0.0000

Data Index: 887161 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 2.8606. Min Range: -2.8606

Max Act: 1.7745. Min Act: -0.0000

Data Index: 1013189 (C4 (Web Text))

Max Activating Token Index: 952