Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 23 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0749. Min Act: -0.0002

Data Index: 263281 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0618. Min Act: -0.0002

Data Index: 508829 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0628. Min Act: -0.0002

Data Index: 659195 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0618. Min Act: -0.0002

Data Index: 185237 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0601. Min Act: -0.0002

Data Index: 960432 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0589. Min Act: -0.0002

Data Index: 271017 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1177106 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0559. Min Act: -0.0002

Data Index: 960579 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0570. Min Act: -0.0002

Data Index: 728589 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0600. Min Act: -0.0002

Data Index: 60777 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0573. Min Act: -0.0002

Data Index: 888829 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1217699 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0568. Min Act: -0.0002

Data Index: 691906 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0566. Min Act: -0.0002

Data Index: 803938 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0556. Min Act: -0.0002

Data Index: 858929 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0557. Min Act: -0.0002

Data Index: 893841 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0558. Min Act: -0.0002

Data Index: 874668 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1065922 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0562. Min Act: -0.0002

Data Index: 853965 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0542. Min Act: -0.0001

Data Index: 689768 (C4 (Web Text))

Max Activating Token Index: 655