Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2696 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0605. Min Act: -0.0002

Data Index: 234612 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1185338 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0749. Min Act: -0.0001

Data Index: 471505 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0700. Min Act: -0.0002

Data Index: 437772 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0681. Min Act: -0.0002

Data Index: 714875 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0656. Min Act: -0.0002

Data Index: 416813 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1357719 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0640. Min Act: -0.0001

Data Index: 930939 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0671. Min Act: -0.0002

Data Index: 5426 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1164730 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1250171 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0652. Min Act: -0.0002

Data Index: 535919 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0635. Min Act: -0.0001

Data Index: 930178 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1306727 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1438 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1206014 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1144598 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0610. Min Act: -0.0002

Data Index: 530772 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1642800 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1092214 (C4 (Web Text))

Max Activating Token Index: 975