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

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

Neuron 1343 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1113. Min Act: -0.0003

Data Index: 743359 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0917. Min Act: -0.0003

Data Index: 566258 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0663. Min Act: -0.0003

Data Index: 676655 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0710. Min Act: -0.0003

Data Index: 778707 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1044371 (C4 (Web Text))

Max Activating Token Index: 769

Text #5

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0742. Min Act: -0.0003

Data Index: 8052 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1232301 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0668. Min Act: -0.0003

Data Index: 114918 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0724. Min Act: -0.0003

Data Index: 21307 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0662. Min Act: -0.0003

Data Index: 630540 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1189461 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1230117 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1029885 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0671. Min Act: -0.0003

Data Index: 393621 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0580. Min Act: -0.0003

Data Index: 645501 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0684. Min Act: -0.0003

Data Index: 1087462 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0621. Min Act: -0.0003

Data Index: 196036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0682. Min Act: -0.0003

Data Index: 588623 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0609. Min Act: -0.0003

Data Index: 544784 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0596. Min Act: -0.0003

Data Index: 144430 (C4 (Web Text))

Max Activating Token Index: 121