Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1774 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0820. Min Act: -0.0002

Data Index: 768030 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0856. Min Act: -0.0002

Data Index: 506226 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0813. Min Act: -0.0002

Data Index: 230197 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0807. Min Act: -0.0002

Data Index: 700020 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0747. Min Act: -0.0002

Data Index: 426291 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0795. Min Act: -0.0002

Data Index: 741342 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0787. Min Act: -0.0002

Data Index: 715159 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0787. Min Act: -0.0002

Data Index: 542439 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1192080 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0754. Min Act: -0.0002

Data Index: 47125 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0766. Min Act: -0.0002

Data Index: 391671 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0782. Min Act: -0.0002

Data Index: 797727 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0793. Min Act: -0.0002

Data Index: 954910 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0708. Min Act: -0.0002

Data Index: 992212 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0743. Min Act: -0.0002

Data Index: 338424 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0771. Min Act: -0.0002

Data Index: 679137 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0804. Min Act: -0.0002

Data Index: 136983 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1289470 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1358370 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0781. Min Act: -0.0002

Data Index: 546259 (C4 (Web Text))

Max Activating Token Index: 854