Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2019 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0885. Min Act: -0.0003

Data Index: 1141629 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0835. Min Act: -0.0004

Data Index: 361879 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0763. Min Act: -0.0003

Data Index: 535122 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0747. Min Act: -0.0003

Data Index: 1054741 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0734. Min Act: -0.0003

Data Index: 287509 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0733. Min Act: -0.0003

Data Index: 554953 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0729. Min Act: -0.0003

Data Index: 412060 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0648. Min Act: -0.0003

Data Index: 610097 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0624. Min Act: -0.0004

Data Index: 449770 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0672. Min Act: -0.0003

Data Index: 543138 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0665. Min Act: -0.0003

Data Index: 621542 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0678. Min Act: -0.0004

Data Index: 1099405 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0685. Min Act: -0.0003

Data Index: 1231204 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0681. Min Act: -0.0003

Data Index: 444339 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0638. Min Act: -0.0003

Data Index: 632971 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0650. Min Act: -0.0003

Data Index: 629948 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1185801 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0646. Min Act: -0.0004

Data Index: 1246728 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0641. Min Act: -0.0003

Data Index: 129798 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0613. Min Act: -0.0004

Data Index: 1179064 (C4 (Web Text))

Max Activating Token Index: 689