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

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

Neuron 3481 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3932. Min Act: -0.0002

Data Index: 820540 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3646. Min Act: -0.0002

Data Index: 1135324 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3515. Min Act: -0.0002

Data Index: 984170 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3369. Min Act: -0.0002

Data Index: 888262 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3319. Min Act: -0.0002

Data Index: 1190350 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3094. Min Act: -0.0002

Data Index: 81581 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3209. Min Act: -0.0002

Data Index: 666895 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3151. Min Act: -0.0002

Data Index: 1290503 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3160. Min Act: -0.0002

Data Index: 1037659 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3131. Min Act: -0.0002

Data Index: 403305 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3067. Min Act: -0.0002

Data Index: 1353452 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3151. Min Act: -0.0002

Data Index: 990298 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2825. Min Act: -0.0002

Data Index: 126819 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2959. Min Act: -0.0002

Data Index: 665393 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2842. Min Act: -0.0002

Data Index: 387922 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2796. Min Act: -0.0002

Data Index: 52884 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.3057. Min Act: -0.0002

Data Index: 1147689 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2737. Min Act: -0.0002

Data Index: 568882 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2837. Min Act: -0.0002

Data Index: 252461 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.3932. Min Range: -0.3932

Max Act: 0.2806. Min Act: -0.0002

Data Index: 1288437 (C4 (Web Text))

Max Activating Token Index: 200