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

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

Neuron 133 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: 0.0923. Min Range: -0.0923

Max Act: 0.0923. Min Act: -0.0004

Data Index: 725172 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0833. Min Act: -0.0003

Data Index: 325764 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0800. Min Act: -0.0004

Data Index: 1010565 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0814. Min Act: -0.0004

Data Index: 698890 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0764. Min Act: -0.0003

Data Index: 406017 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0731. Min Act: -0.0003

Data Index: 158892 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0711. Min Act: -0.0003

Data Index: 551413 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0718. Min Act: -0.0003

Data Index: 750703 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0742. Min Act: -0.0003

Data Index: 846292 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0735. Min Act: -0.0003

Data Index: 255570 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0709. Min Act: -0.0003

Data Index: 646899 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1273342 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0716. Min Act: -0.0003

Data Index: 454788 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0745. Min Act: -0.0003

Data Index: 598592 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0677. Min Act: -0.0003

Data Index: 732253 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0652. Min Act: -0.0004

Data Index: 1187150 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0662. Min Act: -0.0003

Data Index: 62301 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0634. Min Act: -0.0004

Data Index: 979332 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1281243 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0658. Min Act: -0.0003

Data Index: 178395 (C4 (Web Text))

Max Activating Token Index: 296