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

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

Neuron 376 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: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1191566 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0969. Min Act: -0.0002

Data Index: 942067 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0909. Min Act: -0.0002

Data Index: 57354 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0879. Min Act: -0.0002

Data Index: 626257 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1112668 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1006966 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0832. Min Act: -0.0002

Data Index: 64945 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0756. Min Act: -0.0002

Data Index: 323602 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1159449 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0765. Min Act: -0.0002

Data Index: 872844 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0737. Min Act: -0.0002

Data Index: 372575 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0749. Min Act: -0.0002

Data Index: 77474 (C4 (Web Text))

Max Activating Token Index: 733

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0728. Min Act: -0.0002

Data Index: 169353 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1001379 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0711. Min Act: -0.0002

Data Index: 292888 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0753. Min Act: -0.0002

Data Index: 15868 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0714. Min Act: -0.0002

Data Index: 766733 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1171907 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1009762 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0666. Min Act: -0.0002

Data Index: 467241 (C4 (Web Text))

Max Activating Token Index: 641