Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 100 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0787. Min Act: -0.0004

Data Index: 1191802 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0784. Min Act: -0.0004

Data Index: 193031 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0778. Min Act: -0.0003

Data Index: 709259 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0779. Min Act: -0.0003

Data Index: 607928 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0782. Min Act: -0.0003

Data Index: 610273 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0718. Min Act: -0.0002

Data Index: 29859 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0686. Min Act: -0.0003

Data Index: 1027650 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0747. Min Act: -0.0003

Data Index: 543387 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0727. Min Act: -0.0003

Data Index: 368391 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1133835 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1046368 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1047531 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0745. Min Act: -0.0004

Data Index: 519957 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0736. Min Act: -0.0003

Data Index: 194687 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0736. Min Act: -0.0003

Data Index: 26569 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0677. Min Act: -0.0004

Data Index: 424075 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0713. Min Act: -0.0003

Data Index: 1240609 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0715. Min Act: -0.0004

Data Index: 974775 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0714. Min Act: -0.0004

Data Index: 540026 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0700. Min Act: -0.0003

Data Index: 588949 (C4 (Web Text))

Max Activating Token Index: 434