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

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

Neuron 3062 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.1044. Min Act: -0.0002

Data Index: 528009 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0880. Min Act: -0.0002

Data Index: 437896 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1274461 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.1037. Min Act: -0.0002

Data Index: 669414 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0841. Min Act: -0.0002

Data Index: 710545 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0977. Min Act: -0.0002

Data Index: 430017 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0974. Min Act: -0.0002

Data Index: 861876 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0903. Min Act: -0.0002

Data Index: 997173 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1024259 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0868. Min Act: -0.0002

Data Index: 65717 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0961. Min Act: -0.0002

Data Index: 801335 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0828. Min Act: -0.0002

Data Index: 635003 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1194099 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1231146 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0930. Min Act: -0.0002

Data Index: 725377 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0902. Min Act: -0.0002

Data Index: 230854 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0801. Min Act: -0.0002

Data Index: 75749 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0767. Min Act: -0.0002

Data Index: 207725 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0855. Min Act: -0.0002

Data Index: 179316 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1277418 (C4 (Web Text))

Max Activating Token Index: 708