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

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

Neuron 1660 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: 0.0877. Min Range: -0.0877

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1026248 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0853. Min Act: -0.0002

Data Index: 927547 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0833. Min Act: -0.0002

Data Index: 827410 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1212520 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0877. Min Act: -0.0002

Data Index: 620966 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0825. Min Act: -0.0003

Data Index: 1153787 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0768. Min Act: -0.0002

Data Index: 302198 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0836. Min Act: -0.0003

Data Index: 290759 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0802. Min Act: -0.0002

Data Index: 512774 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0779. Min Act: -0.0003

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1200673 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0769. Min Act: -0.0002

Data Index: 134411 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0749. Min Act: -0.0002

Data Index: 151629 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0765. Min Act: -0.0002

Data Index: 599908 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0753. Min Act: -0.0002

Data Index: 969007 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0724. Min Act: -0.0002

Data Index: 579228 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0742. Min Act: -0.0002

Data Index: 196372 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0756. Min Act: -0.0002

Data Index: 41088 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0729. Min Act: -0.0002

Data Index: 561567 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1330366 (C4 (Web Text))

Max Activating Token Index: 729