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

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

Neuron 2012 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0984. Min Act: -0.0000

Data Index: 638111 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1045. Min Act: -0.0000

Data Index: 713933 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0832. Min Act: -0.0000

Data Index: 270898 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0770. Min Act: -0.0000

Data Index: 361057 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0733. Min Act: -0.0000

Data Index: 907744 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1071885 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0760. Min Act: -0.0000

Data Index: 809365 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0683. Min Act: -0.0000

Data Index: 1215380 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0680. Min Act: -0.0000

Data Index: 1277124 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0637. Min Act: -0.0000

Data Index: 270232 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0679. Min Act: -0.0000

Data Index: 799188 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0694. Min Act: -0.0000

Data Index: 363031 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0685. Min Act: -0.0000

Data Index: 726366 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0636. Min Act: -0.0000

Data Index: 75257 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0637. Min Act: -0.0000

Data Index: 426608 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0676. Min Act: -0.0000

Data Index: 775961 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0606. Min Act: -0.0000

Data Index: 366371 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0581. Min Act: -0.0000

Data Index: 456875 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0615. Min Act: -0.0000

Data Index: 769917 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0622. Min Act: -0.0000

Data Index: 694167 (C4 (Web Text))

Max Activating Token Index: 508