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

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

Neuron 540 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: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0002

Data Index: 143860 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0640. Min Act: -0.0002

Data Index: 604827 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0632. Min Act: -0.0002

Data Index: 697024 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0652. Min Act: -0.0002

Data Index: 158226 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0617. Min Act: -0.0002

Data Index: 803852 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1057999 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0605. Min Act: -0.0002

Data Index: 237541 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0635. Min Act: -0.0002

Data Index: 22549 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0642. Min Act: -0.0002

Data Index: 385096 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0616. Min Act: -0.0002

Data Index: 512745 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0617. Min Act: -0.0002

Data Index: 978066 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0606. Min Act: -0.0002

Data Index: 681229 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1032327 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1159277 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0604. Min Act: -0.0002

Data Index: 783984 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0580. Min Act: -0.0002

Data Index: 816275 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0612. Min Act: -0.0002

Data Index: 619973 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0596. Min Act: -0.0002

Data Index: 202487 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0584. Min Act: -0.0002

Data Index: 803492 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0597. Min Act: -0.0002

Data Index: 368248 (C4 (Web Text))

Max Activating Token Index: 203