Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3558 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1246032 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4331. Min Act: -0.0000

Data Index: 318635 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4131. Min Act: -0.0000

Data Index: 582838 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4125. Min Act: -0.0000

Data Index: 54615 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4445. Min Act: -0.0000

Data Index: 983079 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1183048 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4078. Min Act: -0.0000

Data Index: 804717 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1000343 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4066. Min Act: -0.0000

Data Index: 837650 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1013096 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3763. Min Act: -0.0000

Data Index: 622409 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1333413 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3872. Min Act: -0.0000

Data Index: 721667 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3860. Min Act: -0.0000

Data Index: 77892 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1348571 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3914. Min Act: -0.0000

Data Index: 230343 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3756. Min Act: -0.0000

Data Index: 380297 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3902. Min Act: -0.0000

Data Index: 899412 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3795. Min Act: -0.0000

Data Index: 424573 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.5190. Min Range: -0.5190

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1251843 (C4 (Web Text))

Max Activating Token Index: 819