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

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

Neuron 726 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0777. Min Act: -0.0002

Data Index: 18259 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1147238 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0745. Min Act: -0.0002

Data Index: 188816 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0002

Data Index: 771037 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0751. Min Act: -0.0002

Data Index: 913680 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0700. Min Act: -0.0002

Data Index: 515097 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0745. Min Act: -0.0002

Data Index: 63654 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0726. Min Act: -0.0002

Data Index: 409304 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0742. Min Act: -0.0002

Data Index: 802506 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0716. Min Act: -0.0002

Data Index: 279647 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0735. Min Act: -0.0002

Data Index: 12695 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0723. Min Act: -0.0002

Data Index: 441456 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1271772 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0723. Min Act: -0.0002

Data Index: 860977 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0706. Min Act: -0.0002

Data Index: 837506 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0696. Min Act: -0.0002

Data Index: 157307 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0730. Min Act: -0.0002

Data Index: 74952 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0744. Min Act: -0.0002

Data Index: 365457 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0695. Min Act: -0.0002

Data Index: 279193 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1346467 (C4 (Web Text))

Max Activating Token Index: 210