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

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

Neuron 3084 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: 0.8628. Min Range: -0.8628

Max Act: 0.8628. Min Act: -0.0001

Data Index: 63936 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.8023. Min Act: -0.0002

Data Index: 100706 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7858. Min Act: -0.0001

Data Index: 789991 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7444. Min Act: -0.0001

Data Index: 197396 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.8158. Min Act: -0.0002

Data Index: 801787 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7593. Min Act: -0.0002

Data Index: 534074 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7360. Min Act: -0.0001

Data Index: 199580 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7136. Min Act: -0.0001

Data Index: 1132138 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6724. Min Act: -0.0002

Data Index: 1150171 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6674. Min Act: -0.0002

Data Index: 778270 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6792. Min Act: -0.0001

Data Index: 1042160 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6687. Min Act: -0.0001

Data Index: 251748 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6912. Min Act: -0.0002

Data Index: 850250 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.7163. Min Act: -0.0002

Data Index: 533355 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6742. Min Act: -0.0001

Data Index: 1056418 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6796. Min Act: -0.0001

Data Index: 290856 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6612. Min Act: -0.0002

Data Index: 12938 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6419. Min Act: -0.0001

Data Index: 102320 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6565. Min Act: -0.0002

Data Index: 78326 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.8628. Min Range: -0.8628

Max Act: 0.6750. Min Act: -0.0001

Data Index: 1103912 (C4 (Web Text))

Max Activating Token Index: 17