Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4621 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1052. Min Act: -0.0003

Data Index: 440857 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1025. Min Act: -0.0003

Data Index: 567703 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0941. Min Act: -0.0003

Data Index: 145032 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0877. Min Act: -0.0003

Data Index: 70134 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0919. Min Act: -0.0002

Data Index: 5559 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0870. Min Act: -0.0003

Data Index: 1132736 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0900. Min Act: -0.0003

Data Index: 234124 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0850. Min Act: -0.0003

Data Index: 135349 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0865. Min Act: -0.0003

Data Index: 545451 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0784. Min Act: -0.0002

Data Index: 507093 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1107571 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0829. Min Act: -0.0002

Data Index: 40460 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0800. Min Act: -0.0003

Data Index: 802964 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0819. Min Act: -0.0003

Data Index: 953491 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0787. Min Act: -0.0003

Data Index: 599316 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1178752 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0782. Min Act: -0.0003

Data Index: 462390 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0767. Min Act: -0.0003

Data Index: 505653 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0754. Min Act: -0.0003

Data Index: 49490 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1192539 (C4 (Web Text))

Max Activating Token Index: 418