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

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

Neuron 849 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: 0.0908. Min Range: -0.0908

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1230608 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1306621 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0869. Min Act: -0.0002

Data Index: 934314 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0806. Min Act: -0.0002

Data Index: 855193 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0756. Min Act: -0.0002

Data Index: 407291 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0746. Min Act: -0.0002

Data Index: 803006 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1261282 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0739. Min Act: -0.0002

Data Index: 805121 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0636. Min Act: -0.0002

Data Index: 977275 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0705. Min Act: -0.0002

Data Index: 976183 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0674. Min Act: -0.0002

Data Index: 698309 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0734. Min Act: -0.0002

Data Index: 335718 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0830. Min Act: -0.0002

Data Index: 459090 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0734. Min Act: -0.0002

Data Index: 794864 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1158854 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1027482 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1207387 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0688. Min Act: -0.0002

Data Index: 543703 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0716. Min Act: -0.0002

Data Index: 914049 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0683. Min Act: -0.0002

Data Index: 715482 (C4 (Web Text))

Max Activating Token Index: 163