Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.1061. Min Act: -0.0000

Data Index: 322083 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0772. Min Act: -0.0000

Data Index: 658225 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0788. Min Act: -0.0000

Data Index: 17050 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0827. Min Act: -0.0000

Data Index: 498509 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0845. Min Act: -0.0000

Data Index: 995834 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0792. Min Act: -0.0000

Data Index: 941114 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0828. Min Act: -0.0000

Data Index: 149120 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0796. Min Act: -0.0000

Data Index: 444522 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0819. Min Act: -0.0000

Data Index: 737789 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0755. Min Act: -0.0000

Data Index: 765415 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1020789 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0806. Min Act: -0.0000

Data Index: 456426 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0763. Min Act: -0.0000

Data Index: 719282 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0705. Min Act: -0.0000

Data Index: 785004 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0714. Min Act: -0.0000

Data Index: 302816 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0756. Min Act: -0.0000

Data Index: 534625 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0671. Min Act: -0.0000

Data Index: 228539 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0693. Min Act: -0.0000

Data Index: 975691 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0689. Min Act: -0.0000

Data Index: 201220 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0728. Min Act: -0.0000

Data Index: 425662 (C4 (Web Text))

Max Activating Token Index: 484