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

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

Neuron 2643 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0946. Min Act: -0.0003

Data Index: 833735 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0909. Min Act: -0.0003

Data Index: 985656 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0847. Min Act: -0.0003

Data Index: 584025 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0793. Min Act: -0.0003

Data Index: 403039 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0856. Min Act: -0.0003

Data Index: 121683 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0691. Min Act: -0.0003

Data Index: 103711 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0794. Min Act: -0.0003

Data Index: 1053533 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0790. Min Act: -0.0003

Data Index: 928455 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1332110 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0772. Min Act: -0.0003

Data Index: 192590 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0796. Min Act: -0.0003

Data Index: 510843 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1069051 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1020007 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0811. Min Act: -0.0003

Data Index: 291430 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0828. Min Act: -0.0003

Data Index: 89129 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0779. Min Act: -0.0003

Data Index: 995142 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0825. Min Act: -0.0003

Data Index: 728511 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0778. Min Act: -0.0003

Data Index: 864832 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0798. Min Act: -0.0003

Data Index: 545467 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0762. Min Act: -0.0003

Data Index: 328355 (C4 (Web Text))

Max Activating Token Index: 963