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

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

Neuron 5091 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0001

Data Index: 114523 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1318850 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0823. Min Act: -0.0001

Data Index: 728871 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0818. Min Act: -0.0001

Data Index: 332684 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0679. Min Act: -0.0002

Data Index: 15501 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0800. Min Act: -0.0001

Data Index: 795512 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0816. Min Act: -0.0001

Data Index: 246971 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0844. Min Act: -0.0001

Data Index: 182525 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0740. Min Act: -0.0001

Data Index: 322485 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0758. Min Act: -0.0001

Data Index: 529526 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1278709 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1126386 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0919. Min Act: -0.0001

Data Index: 360424 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0757. Min Act: -0.0001

Data Index: 776409 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0786. Min Act: -0.0001

Data Index: 420428 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0778. Min Act: -0.0001

Data Index: 570560 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0775. Min Act: -0.0001

Data Index: 306742 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1318616 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0665. Min Act: -0.0001

Data Index: 281930 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0715. Min Act: -0.0001

Data Index: 211716 (C4 (Web Text))

Max Activating Token Index: 409