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

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

Neuron 608 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: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0002

Data Index: 662972 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1081042 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0824. Min Act: -0.0002

Data Index: 938614 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0831. Min Act: -0.0002

Data Index: 932852 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1114388 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0769. Min Act: -0.0002

Data Index: 863980 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1212669 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1152408 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0785. Min Act: -0.0002

Data Index: 163799 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1077581 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0751. Min Act: -0.0002

Data Index: 247710 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0753. Min Act: -0.0002

Data Index: 618941 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0749. Min Act: -0.0002

Data Index: 960508 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0741. Min Act: -0.0002

Data Index: 136190 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0740. Min Act: -0.0002

Data Index: 211793 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0753. Min Act: -0.0002

Data Index: 347257 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0697. Min Act: -0.0002

Data Index: 814941 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0714. Min Act: -0.0002

Data Index: 185350 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0716. Min Act: -0.0002

Data Index: 25858 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0717. Min Act: -0.0002

Data Index: 923310 (C4 (Web Text))

Max Activating Token Index: 918