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

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

Neuron 934 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: 0.3609. Min Range: -0.3609

Max Act: 0.3609. Min Act: -0.0002

Data Index: 1111073 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.3494. Min Act: -0.0002

Data Index: 387722 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.3218. Min Act: -0.0002

Data Index: 832652 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2963. Min Act: -0.0002

Data Index: 87093 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.3101. Min Act: -0.0002

Data Index: 1298456 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2841. Min Act: -0.0002

Data Index: 743383 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.3001. Min Act: -0.0002

Data Index: 355386 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.3067. Min Act: -0.0002

Data Index: 721379 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2873. Min Act: -0.0002

Data Index: 249243 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2860. Min Act: -0.0002

Data Index: 1066002 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2949. Min Act: -0.0002

Data Index: 1212192 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2901. Min Act: -0.0002

Data Index: 203097 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2730. Min Act: -0.0002

Data Index: 549946 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2805. Min Act: -0.0002

Data Index: 888573 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2711. Min Act: -0.0002

Data Index: 808065 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2694. Min Act: -0.0002

Data Index: 188896 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2925. Min Act: -0.0002

Data Index: 1303348 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2734. Min Act: -0.0002

Data Index: 1032295 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2585. Min Act: -0.0002

Data Index: 826833 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.3609. Min Range: -0.3609

Max Act: 0.2830. Min Act: -0.0002

Data Index: 181495 (C4 (Web Text))

Max Activating Token Index: 498