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

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

Neuron 555 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: 0.0992. Min Range: -0.0992

Max Act: 0.0992. Min Act: -0.0004

Data Index: 1065224 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0933. Min Act: -0.0004

Data Index: 517202 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0882. Min Act: -0.0004

Data Index: 233547 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0727. Min Act: -0.0004

Data Index: 175863 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0827. Min Act: -0.0004

Data Index: 542420 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0781. Min Act: -0.0004

Data Index: 189621 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0756. Min Act: -0.0004

Data Index: 369448 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0755. Min Act: -0.0004

Data Index: 1003951 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0909. Min Act: -0.0004

Data Index: 86784 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0727. Min Act: -0.0004

Data Index: 991779 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0662. Min Act: -0.0004

Data Index: 121748 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0766. Min Act: -0.0004

Data Index: 441877 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0655. Min Act: -0.0004

Data Index: 356245 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0855. Min Act: -0.0004

Data Index: 463928 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0789. Min Act: -0.0004

Data Index: 120558 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0749. Min Act: -0.0004

Data Index: 109481 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0720. Min Act: -0.0004

Data Index: 1132400 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0719. Min Act: -0.0004

Data Index: 575677 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0770. Min Act: -0.0004

Data Index: 290148 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.0992. Min Range: -0.0992

Max Act: 0.0793. Min Act: -0.0004

Data Index: 165201 (C4 (Web Text))

Max Activating Token Index: 561