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

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

Neuron 1279 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: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: -0.0002

Data Index: 684210 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0724. Min Act: -0.0002

Data Index: 590867 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0721. Min Act: -0.0003

Data Index: 260511 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0710. Min Act: -0.0003

Data Index: 857151 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0685. Min Act: -0.0003

Data Index: 680426 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0682. Min Act: -0.0003

Data Index: 398484 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0689. Min Act: -0.0003

Data Index: 454542 (C4 (Web Text))

Max Activating Token Index: 470

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0662. Min Act: -0.0003

Data Index: 1035475 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1187577 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0653. Min Act: -0.0002

Data Index: 99987 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0656. Min Act: -0.0003

Data Index: 34647 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0666. Min Act: -0.0002

Data Index: 676065 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0655. Min Act: -0.0003

Data Index: 666961 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0658. Min Act: -0.0002

Data Index: 876046 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1003228 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1238623 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0632. Min Act: -0.0004

Data Index: 410714 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0646. Min Act: -0.0003

Data Index: 510714 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0636. Min Act: -0.0003

Data Index: 409067 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0651. Min Act: -0.0003

Data Index: 704410 (C4 (Web Text))

Max Activating Token Index: 859