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

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

Neuron 3757 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0862. Min Act: -0.0001

Data Index: 589013 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0771. Min Act: -0.0002

Data Index: 113343 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1023876 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0820. Min Act: -0.0001

Data Index: 552201 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0748. Min Act: -0.0002

Data Index: 582348 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0823. Min Act: -0.0002

Data Index: 735686 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0779. Min Act: -0.0002

Data Index: 387887 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1120656 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0800. Min Act: -0.0001

Data Index: 717024 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1131313 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0819. Min Act: -0.0002

Data Index: 692851 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1188229 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0876. Min Act: -0.0001

Data Index: 779858 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0841. Min Act: -0.0001

Data Index: 735084 (C4 (Web Text))

Max Activating Token Index: 343

Text #14

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0776. Min Act: -0.0001

Data Index: 71467 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1264968 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0724. Min Act: -0.0002

Data Index: 36513 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0738. Min Act: -0.0002

Data Index: 309954 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0815. Min Act: -0.0002

Data Index: 783283 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0693. Min Act: -0.0002

Data Index: 528395 (C4 (Web Text))

Max Activating Token Index: 908