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

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

Neuron 3797 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0924. Min Range: -2.0924

Max Act: 2.0924. Min Act: -0.0000

Data Index: 90389 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.6942. Min Act: -0.0000

Data Index: 498619 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.2887. Min Act: -0.0000

Data Index: 82510 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 2.0924. Min Range: -2.0924

Max Act: 1.1426. Min Act: -0.0000

Data Index: 1358164 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.9242. Min Act: -0.0000

Data Index: 870151 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.9345. Min Act: -0.0000

Data Index: 313106 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.9117. Min Act: -0.0000

Data Index: 673764 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.8859. Min Act: -0.0000

Data Index: 324287 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.8166. Min Act: -0.0000

Data Index: 900514 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1013595 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1290512 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.8487. Min Act: -0.0000

Data Index: 379631 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.7217. Min Act: -0.0000

Data Index: 577763 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.7157. Min Act: -0.0000

Data Index: 722519 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.6984. Min Act: -0.0000

Data Index: 350620 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.6371. Min Act: -0.0000

Data Index: 666700 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.6753. Min Act: -0.0000

Data Index: 650823 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1123179 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.6305. Min Act: -0.0000

Data Index: 321468 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 2.0924. Min Range: -2.0924

Max Act: 0.6546. Min Act: -0.0000

Data Index: 20668 (C4 (Web Text))

Max Activating Token Index: 977