Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1886 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0960. Min Act: -0.0003

Data Index: 607465 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0840. Min Act: -0.0004

Data Index: 847743 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0924. Min Act: -0.0003

Data Index: 1091853 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1017. Min Act: -0.0003

Data Index: 96175 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0857. Min Act: -0.0003

Data Index: 978005 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0877. Min Act: -0.0003

Data Index: 264167 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0895. Min Act: -0.0003

Data Index: 706217 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0890. Min Act: -0.0003

Data Index: 411132 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0851. Min Act: -0.0003

Data Index: 964580 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1061. Min Act: -0.0003

Data Index: 440653 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0931. Min Act: -0.0003

Data Index: 1005866 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0927. Min Act: -0.0003

Data Index: 1037739 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0856. Min Act: -0.0003

Data Index: 482697 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0820. Min Act: -0.0003

Data Index: 404438 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0865. Min Act: -0.0003

Data Index: 32095 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0933. Min Act: -0.0003

Data Index: 936293 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0936. Min Act: -0.0003

Data Index: 533288 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0857. Min Act: -0.0003

Data Index: 155741 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0783. Min Act: -0.0003

Data Index: 821037 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0816. Min Act: -0.0003

Data Index: 621122 (C4 (Web Text))

Max Activating Token Index: 650