Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1408 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0694. Min Act: -0.0003

Data Index: 57577 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0681. Min Act: -0.0004

Data Index: 119344 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0662. Min Act: -0.0003

Data Index: 4006 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0609. Min Act: -0.0004

Data Index: 873931 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0652. Min Act: -0.0003

Data Index: 712274 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0609. Min Act: -0.0003

Data Index: 143719 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0615. Min Act: -0.0004

Data Index: 709575 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0599. Min Act: -0.0003

Data Index: 772747 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0612. Min Act: -0.0003

Data Index: 515904 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1140260 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1185714 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0587. Min Act: -0.0003

Data Index: 1011424 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0579. Min Act: -0.0003

Data Index: 853978 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0589. Min Act: -0.0002

Data Index: 992342 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0589. Min Act: -0.0003

Data Index: 871258 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0582. Min Act: -0.0003

Data Index: 385728 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0579. Min Act: -0.0003

Data Index: 387826 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0577. Min Act: -0.0003

Data Index: 701824 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0558. Min Act: -0.0003

Data Index: 126418 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0570. Min Act: -0.0004

Data Index: 1082646 (C4 (Web Text))

Max Activating Token Index: 35