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

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

Neuron 238 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: 0.0801. Min Range: -0.0801

Max Act: 0.0801. Min Act: -0.0002

Data Index: 983286 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1357751 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0781. Min Act: -0.0002

Data Index: 11481 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0775. Min Act: -0.0002

Data Index: 619488 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0767. Min Act: -0.0002

Data Index: 600076 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0749. Min Act: -0.0002

Data Index: 240206 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0729. Min Act: -0.0002

Data Index: 203383 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0725. Min Act: -0.0002

Data Index: 684610 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0730. Min Act: -0.0002

Data Index: 26299 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0732. Min Act: -0.0002

Data Index: 362280 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0714. Min Act: -0.0002

Data Index: 13965 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1009914 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1301423 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0717. Min Act: -0.0002

Data Index: 209962 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0714. Min Act: -0.0002

Data Index: 690407 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0723. Min Act: -0.0002

Data Index: 322355 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0711. Min Act: -0.0002

Data Index: 842738 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1227218 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0694. Min Act: -0.0002

Data Index: 977967 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0698. Min Act: -0.0002

Data Index: 52213 (C4 (Web Text))

Max Activating Token Index: 489