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

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

Neuron 1747 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: 0.0877. Min Range: -0.0877

Max Act: 0.0877. Min Act: -0.0003

Data Index: 668730 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0788. Min Act: -0.0003

Data Index: 741406 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0720. Min Act: -0.0003

Data Index: 799114 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0684. Min Act: -0.0003

Data Index: 315486 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1078075 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1335679 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0642. Min Act: -0.0003

Data Index: 695456 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0612. Min Act: -0.0003

Data Index: 787919 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0628. Min Act: -0.0003

Data Index: 658604 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0625. Min Act: -0.0003

Data Index: 774955 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0617. Min Act: -0.0003

Data Index: 15055 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0590. Min Act: -0.0003

Data Index: 281887 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1308384 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1069101 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0592. Min Act: -0.0004

Data Index: 184842 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1149531 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1284605 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0587. Min Act: -0.0003

Data Index: 991571 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0603. Min Act: -0.0002

Data Index: 299869 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0558. Min Act: -0.0003

Data Index: 372111 (C4 (Web Text))

Max Activating Token Index: 800