Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 492 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0004

Data Index: 7228 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0780. Min Act: -0.0003

Data Index: 726481 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0811. Min Act: -0.0003

Data Index: 459754 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0789. Min Act: -0.0003

Data Index: 869882 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0742. Min Act: -0.0003

Data Index: 911038 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1211262 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0721. Min Act: -0.0003

Data Index: 743535 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0719. Min Act: -0.0004

Data Index: 196242 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0721. Min Act: -0.0004

Data Index: 1004349 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1281983 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1285082 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1179924 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0672. Min Act: -0.0004

Data Index: 1305741 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0648. Min Act: -0.0003

Data Index: 290719 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0691. Min Act: -0.0004

Data Index: 694000 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1174322 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1322098 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0665. Min Act: -0.0003

Data Index: 70932 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0662. Min Act: -0.0004

Data Index: 81290 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0674. Min Act: -0.0003

Data Index: 657419 (C4 (Web Text))

Max Activating Token Index: 112