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

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

Neuron 724 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1198. Min Act: -0.0001

Data Index: 582590 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1282664 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0914. Min Act: -0.0001

Data Index: 1024172 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0954. Min Act: -0.0001

Data Index: 835635 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0978. Min Act: -0.0001

Data Index: 807720 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0931. Min Act: -0.0001

Data Index: 733164 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0821. Min Act: -0.0001

Data Index: 809419 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1231864 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1354682 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0962. Min Act: -0.0001

Data Index: 463731 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0763. Min Act: -0.0001

Data Index: 772649 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0846. Min Act: -0.0001

Data Index: 564695 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0712. Min Act: -0.0001

Data Index: 492899 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1186609 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0868. Min Act: -0.0002

Data Index: 613722 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0883. Min Act: -0.0001

Data Index: 380413 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1178747 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0876. Min Act: -0.0001

Data Index: 867196 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1131451 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.1198. Min Range: -0.1198

Max Act: 0.0829. Min Act: -0.0001

Data Index: 142546 (C4 (Web Text))

Max Activating Token Index: 27