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

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

Neuron 5195 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.8719. Min Act: -0.0002

Data Index: 437614 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7689. Min Act: -0.0002

Data Index: 809325 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7691. Min Act: -0.0002

Data Index: 987065 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7684. Min Act: -0.0002

Data Index: 49081 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7406. Min Act: -0.0002

Data Index: 195513 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7247. Min Act: -0.0002

Data Index: 1240296 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7494. Min Act: -0.0002

Data Index: 1162750 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7234. Min Act: -0.0002

Data Index: 658308 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7159. Min Act: -0.0002

Data Index: 1092188 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7331. Min Act: -0.0002

Data Index: 328899 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6848. Min Act: -0.0002

Data Index: 887702 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.7095. Min Act: -0.0002

Data Index: 276675 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6870. Min Act: -0.0002

Data Index: 1077599 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6806. Min Act: -0.0002

Data Index: 181703 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6631. Min Act: -0.0002

Data Index: 759007 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6570. Min Act: -0.0002

Data Index: 1180490 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6972. Min Act: -0.0002

Data Index: 223201 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6962. Min Act: -0.0002

Data Index: 279674 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6675. Min Act: -0.0002

Data Index: 589805 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.8719. Min Range: -0.8719

Max Act: 0.6670. Min Act: -0.0002

Data Index: 534434 (C4 (Web Text))

Max Activating Token Index: 49