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

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

Neuron 2959 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: 0.1129. Min Range: -0.1129

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1256483 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0859. Min Act: -0.0002

Data Index: 841943 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0790. Min Act: -0.0002

Data Index: 853484 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0798. Min Act: -0.0002

Data Index: 733784 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0847. Min Act: -0.0002

Data Index: 190351 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1116949 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1196605 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1108426 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0764. Min Act: -0.0002

Data Index: 216502 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1246490 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0629. Min Act: -0.0002

Data Index: 34893 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0686. Min Act: -0.0002

Data Index: 931086 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0653. Min Act: -0.0002

Data Index: 39075 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0638. Min Act: -0.0002

Data Index: 889087 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1120711 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1071826 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0671. Min Act: -0.0002

Data Index: 76412 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0670. Min Act: -0.0002

Data Index: 113341 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0521. Min Act: -0.0002

Data Index: 228158 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 0.1129. Min Range: -0.1129

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1267970 (C4 (Web Text))

Max Activating Token Index: 489