Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1523 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0005

Data Index: 1026412 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0745. Min Act: -0.0005

Data Index: 921873 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0743. Min Act: -0.0005

Data Index: 672698 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0732. Min Act: -0.0005

Data Index: 829359 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0730. Min Act: -0.0005

Data Index: 215195 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0742. Min Act: -0.0005

Data Index: 159530 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0730. Min Act: -0.0005

Data Index: 1130732 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0732. Min Act: -0.0005

Data Index: 936593 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0686. Min Act: -0.0005

Data Index: 806208 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0696. Min Act: -0.0005

Data Index: 1098260 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0682. Min Act: -0.0005

Data Index: 273819 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0676. Min Act: -0.0005

Data Index: 672088 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0677. Min Act: -0.0005

Data Index: 648846 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0675. Min Act: -0.0005

Data Index: 661410 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0660. Min Act: -0.0005

Data Index: 728509 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0685. Min Act: -0.0005

Data Index: 1017518 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0696. Min Act: -0.0005

Data Index: 274571 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0671. Min Act: -0.0005

Data Index: 664929 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0661. Min Act: -0.0005

Data Index: 196258 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0660. Min Act: -0.0005

Data Index: 1010871 (C4 (Web Text))

Max Activating Token Index: 832