Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1082 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0777. Min Act: -0.0003

Data Index: 786839 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: -0.0003

Data Index: 820684 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0776. Min Act: -0.0003

Data Index: 1241644 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0755. Min Act: -0.0003

Data Index: 878668 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1265885 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0706. Min Act: -0.0003

Data Index: 99349 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0708. Min Act: -0.0003

Data Index: 314445 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0748. Min Act: -0.0003

Data Index: 245381 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0720. Min Act: -0.0003

Data Index: 618800 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0678. Min Act: -0.0003

Data Index: 740711 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1340691 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0694. Min Act: -0.0003

Data Index: 267323 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0706. Min Act: -0.0003

Data Index: 62272 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1180748 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0655. Min Act: -0.0003

Data Index: 254337 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0671. Min Act: -0.0003

Data Index: 754277 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0672. Min Act: -0.0003

Data Index: 665725 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0663. Min Act: -0.0003

Data Index: 65441 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1093045 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0661. Min Act: -0.0003

Data Index: 613635 (C4 (Web Text))

Max Activating Token Index: 837