Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1499 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0003

Data Index: 35818 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0748. Min Act: -0.0003

Data Index: 1617468 (Python Code)

Max Activating Token Index: 448

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0702. Min Act: -0.0003

Data Index: 798134 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0696. Min Act: -0.0003

Data Index: 822659 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0678. Min Act: -0.0003

Data Index: 1243899 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1337117 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0658. Min Act: -0.0003

Data Index: 817804 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1215053 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0668. Min Act: -0.0003

Data Index: 266713 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0683. Min Act: -0.0003

Data Index: 330219 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0686. Min Act: -0.0003

Data Index: 961438 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0692. Min Act: -0.0003

Data Index: 311294 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1648198 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0611. Min Act: -0.0003

Data Index: 905244 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0650. Min Act: -0.0003

Data Index: 409525 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1543202 (Python Code)

Max Activating Token Index: 992

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0590. Min Act: -0.0003

Data Index: 878075 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1036070 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0653. Min Act: -0.0003

Data Index: 685888 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0618. Min Act: -0.0003

Data Index: 595129 (C4 (Web Text))

Max Activating Token Index: 323