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

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

Neuron 595 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: 1.1974. Min Range: -1.1974

Max Act: 1.1914. Min Act: -0.0000

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1002. Min Act: -0.0000

Data Index: 169207 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1974. Min Act: -0.0000

Data Index: 558106 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0832. Min Act: -0.0000

Data Index: 298011 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1017963 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1354650 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0510. Min Act: -0.0000

Data Index: 419818 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0316. Min Act: -0.0000

Data Index: 67368 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1219334 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0082. Min Act: -0.0000

Data Index: 533658 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.9459. Min Act: -0.0000

Data Index: 111549 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1150230 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.9815. Min Act: -0.0000

Data Index: 270975 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.9602. Min Act: -0.0000

Data Index: 662913 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1288388 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.9923. Min Act: -0.0000

Data Index: 234752 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.9287. Min Act: 0.0000

Data Index: 325874 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.8672. Min Act: 0.0001

Data Index: 265630 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.9143. Min Act: 0.0000

Data Index: 208028 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.1974. Min Range: -1.1974

Max Act: 0.8880. Min Act: -0.0000

Data Index: 655992 (C4 (Web Text))

Max Activating Token Index: 233