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

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

Neuron 1799 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: 0.0912. Min Range: -0.0912

Max Act: 0.0912. Min Act: -0.0002

Data Index: 759599 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0854. Min Act: -0.0002

Data Index: 151079 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0760. Min Act: -0.0002

Data Index: 414269 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0754. Min Act: -0.0002

Data Index: 362191 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1038706 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0745. Min Act: -0.0002

Data Index: 922121 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0728. Min Act: -0.0002

Data Index: 49831 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1001045 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0735. Min Act: -0.0002

Data Index: 613106 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0721. Min Act: -0.0002

Data Index: 157471 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0740. Min Act: -0.0001

Data Index: 1020331 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0732. Min Act: -0.0002

Data Index: 399390 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1062063 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0692. Min Act: -0.0002

Data Index: 844348 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0706. Min Act: -0.0001

Data Index: 859215 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0686. Min Act: -0.0002

Data Index: 670196 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1050072 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0664. Min Act: -0.0002

Data Index: 97909 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0702. Min Act: -0.0002

Data Index: 501416 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1139814 (C4 (Web Text))

Max Activating Token Index: 365