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

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

Neuron 643 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: 0.0983. Min Range: -0.0983

Max Act: 0.0983. Min Act: -0.0002

Data Index: 286812 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1078866 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0878. Min Act: -0.0003

Data Index: 1647434 (Python Code)

Max Activating Token Index: 320

Text #3

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0829. Min Act: -0.0003

Data Index: 701737 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0800. Min Act: -0.0003

Data Index: 417277 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1451324 (Python Code)

Max Activating Token Index: 653

Text #6

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0733. Min Act: -0.0003

Data Index: 186020 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0701. Min Act: -0.0003

Data Index: 991874 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0686. Min Act: -0.0002

Data Index: 238254 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0744. Min Act: -0.0003

Data Index: 697197 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1303440 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0693. Min Act: -0.0003

Data Index: 1179872 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0672. Min Act: -0.0003

Data Index: 942058 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0663. Min Act: -0.0002

Data Index: 788786 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0662. Min Act: -0.0003

Data Index: 1652430 (Python Code)

Max Activating Token Index: 332

Text #15

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0673. Min Act: -0.0003

Data Index: 57582 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1368835 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1489369 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1638129 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 0.0983. Min Range: -0.0983

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1559841 (Python Code)

Max Activating Token Index: 206