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

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

Neuron 398 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0958. Min Act: -0.0002

Data Index: 779965 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0952. Min Act: -0.0002

Data Index: 638542 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0919. Min Act: -0.0002

Data Index: 809893 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0921. Min Act: -0.0002

Data Index: 697722 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0888. Min Act: -0.0002

Data Index: 552359 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0857. Min Act: -0.0002

Data Index: 544304 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0888. Min Act: -0.0002

Data Index: 257593 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0875. Min Act: -0.0002

Data Index: 117346 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0833. Min Act: -0.0002

Data Index: 427491 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1109862 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0779. Min Act: -0.0002

Data Index: 652242 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0870. Min Act: -0.0002

Data Index: 846919 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0842. Min Act: -0.0002

Data Index: 387365 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1225379 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0838. Min Act: -0.0002

Data Index: 752728 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1022696 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1109836 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0829. Min Act: -0.0002

Data Index: 981516 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1262401 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0824. Min Act: -0.0002

Data Index: 885337 (C4 (Web Text))

Max Activating Token Index: 5