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

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

Neuron 2049 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1004. Min Act: -0.0003

Data Index: 61525 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0002

Data Index: 982452 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0980. Min Act: -0.0002

Data Index: 792152 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0959. Min Act: -0.0002

Data Index: 114741 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1163224 (C4 (Web Text))

Max Activating Token Index: 291

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1090599 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0876. Min Act: -0.0002

Data Index: 492185 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0828. Min Act: -0.0002

Data Index: 499848 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1193349 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0797. Min Act: -0.0002

Data Index: 199079 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1170141 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0766. Min Act: -0.0002

Data Index: 250727 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0792. Min Act: -0.0003

Data Index: 33471 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1624952 (Python Code)

Max Activating Token Index: 320

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1620945 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1354985 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0773. Min Act: -0.0002

Data Index: 961128 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1628322 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0745. Min Act: -0.0003

Data Index: 243486 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0756. Min Act: -0.0002

Data Index: 88882 (C4 (Web Text))

Max Activating Token Index: 594