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

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

Neuron 351 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: 0.0937. Min Range: -0.0937

Max Act: 0.0937. Min Act: -0.0002

Data Index: 266824 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1072269 (C4 (Web Text))

Max Activating Token Index: 400

Text #2

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1016821 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0884. Min Act: -0.0002

Data Index: 232220 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0894. Min Act: -0.0002

Data Index: 973337 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0870. Min Act: -0.0002

Data Index: 850168 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0868. Min Act: -0.0002

Data Index: 893244 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0820. Min Act: -0.0002

Data Index: 396 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0797. Min Act: -0.0002

Data Index: 322363 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0820. Min Act: -0.0002

Data Index: 248102 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0801. Min Act: -0.0002

Data Index: 619986 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1093011 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0819. Min Act: -0.0002

Data Index: 906211 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1152238 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1295199 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1231244 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0765. Min Act: -0.0002

Data Index: 4600 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0756. Min Act: -0.0002

Data Index: 32373 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0755. Min Act: -0.0002

Data Index: 247055 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.0937. Min Range: -0.0937

Max Act: 0.0765. Min Act: -0.0002

Data Index: 550035 (C4 (Web Text))

Max Activating Token Index: 436