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

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

Neuron 440 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1012. Min Act: -0.0004

Data Index: 1261910 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0910. Min Act: -0.0004

Data Index: 1210403 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0838. Min Act: -0.0004

Data Index: 1347477 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0869. Min Act: -0.0004

Data Index: 837813 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0834. Min Act: -0.0004

Data Index: 201629 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1150290 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0824. Min Act: -0.0004

Data Index: 1050133 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0853. Min Act: -0.0004

Data Index: 1202284 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0813. Min Act: -0.0004

Data Index: 1124283 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0815. Min Act: -0.0004

Data Index: 1276794 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0815. Min Act: -0.0004

Data Index: 627216 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0775. Min Act: -0.0004

Data Index: 674166 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0762. Min Act: -0.0004

Data Index: 566005 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0741. Min Act: -0.0004

Data Index: 121506 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0759. Min Act: -0.0004

Data Index: 655362 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0749. Min Act: -0.0004

Data Index: 658717 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0700. Min Act: -0.0004

Data Index: 159224 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0747. Min Act: -0.0004

Data Index: 1075076 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0718. Min Act: -0.0004

Data Index: 1265597 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0716. Min Act: -0.0004

Data Index: 360109 (C4 (Web Text))

Max Activating Token Index: 304