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

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

Neuron 1542 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0002

Data Index: 20740 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0624. Min Act: -0.0002

Data Index: 564168 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0617. Min Act: -0.0002

Data Index: 558736 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0614. Min Act: -0.0002

Data Index: 471156 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0604. Min Act: -0.0002

Data Index: 243576 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0602. Min Act: -0.0002

Data Index: 82459 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0600. Min Act: -0.0002

Data Index: 801366 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0589. Min Act: -0.0002

Data Index: 752713 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0578. Min Act: -0.0002

Data Index: 739805 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0576. Min Act: -0.0002

Data Index: 765662 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1045581 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1168292 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0570. Min Act: -0.0002

Data Index: 374814 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0545. Min Act: -0.0002

Data Index: 517157 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0560. Min Act: -0.0002

Data Index: 943452 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0559. Min Act: -0.0002

Data Index: 86496 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0558. Min Act: -0.0002

Data Index: 417488 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0558. Min Act: -0.0002

Data Index: 12756 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0556. Min Act: -0.0002

Data Index: 365285 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0555. Min Act: -0.0002

Data Index: 274391 (C4 (Web Text))

Max Activating Token Index: 118