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

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

Neuron 449 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: 0.0909. Min Range: -0.0909

Max Act: 0.0909. Min Act: -0.0002

Data Index: 347983 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0868. Min Act: -0.0002

Data Index: 997205 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0856. Min Act: -0.0002

Data Index: 876258 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0781. Min Act: -0.0002

Data Index: 368177 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1277051 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0775. Min Act: -0.0002

Data Index: 359799 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0735. Min Act: -0.0002

Data Index: 289224 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0767. Min Act: -0.0002

Data Index: 905145 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0758. Min Act: -0.0002

Data Index: 377266 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0744. Min Act: -0.0002

Data Index: 517329 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0720. Min Act: -0.0002

Data Index: 46825 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0746. Min Act: -0.0002

Data Index: 765144 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0760. Min Act: -0.0002

Data Index: 623891 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0718. Min Act: -0.0002

Data Index: 702717 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0702. Min Act: -0.0002

Data Index: 666648 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0770. Min Act: -0.0002

Data Index: 796711 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1275887 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0708. Min Act: -0.0002

Data Index: 838566 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1071270 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0724. Min Act: -0.0002

Data Index: 967010 (C4 (Web Text))

Max Activating Token Index: 482