Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1611 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1061. Min Act: -0.0003

Data Index: 763785 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1007. Min Act: -0.0003

Data Index: 257843 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1011. Min Act: -0.0003

Data Index: 241058 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1005. Min Act: -0.0003

Data Index: 1121446 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1002. Min Act: -0.0003

Data Index: 1267912 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0945. Min Act: -0.0003

Data Index: 81822 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0924. Min Act: -0.0003

Data Index: 645337 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0970. Min Act: -0.0003

Data Index: 210892 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0947. Min Act: -0.0003

Data Index: 85159 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0941. Min Act: -0.0003

Data Index: 1125715 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0940. Min Act: -0.0003

Data Index: 9159 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0890. Min Act: -0.0002

Data Index: 817958 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0934. Min Act: -0.0003

Data Index: 1351010 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0888. Min Act: -0.0003

Data Index: 459470 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0922. Min Act: -0.0003

Data Index: 1148482 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0904. Min Act: -0.0003

Data Index: 581937 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0937. Min Act: -0.0003

Data Index: 581550 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1025160 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0906. Min Act: -0.0003

Data Index: 998529 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0884. Min Act: -0.0003

Data Index: 349022 (C4 (Web Text))

Max Activating Token Index: 483