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

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

Neuron 1211 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: 0.1074. Min Range: -0.1074

Max Act: 0.1074. Min Act: -0.0003

Data Index: 78259 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0897. Min Act: -0.0003

Data Index: 1336082 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1116456 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0796. Min Act: -0.0004

Data Index: 1302497 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0746. Min Act: -0.0004

Data Index: 1175986 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0755. Min Act: -0.0003

Data Index: 133805 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0729. Min Act: -0.0003

Data Index: 230931 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0736. Min Act: -0.0004

Data Index: 665870 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1241945 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0680. Min Act: -0.0003

Data Index: 861007 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0735. Min Act: -0.0003

Data Index: 1206749 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0746. Min Act: -0.0003

Data Index: 214151 (C4 (Web Text))

Max Activating Token Index: 983

Text #12

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0765. Min Act: -0.0004

Data Index: 1354773 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0753. Min Act: -0.0003

Data Index: 26066 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0684. Min Act: -0.0003

Data Index: 214346 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0721. Min Act: -0.0003

Data Index: 550153 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0744. Min Act: -0.0003

Data Index: 134514 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0713. Min Act: -0.0003

Data Index: 208975 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0707. Min Act: -0.0003

Data Index: 668706 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.1074. Min Range: -0.1074

Max Act: 0.0719. Min Act: -0.0003

Data Index: 810794 (C4 (Web Text))

Max Activating Token Index: 682