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

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

Neuron 3216 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.5467. Min Act: -0.0000

Data Index: 1217541 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.6351. Min Act: -0.0000

Data Index: 1028224 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1174285 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.3515. Min Act: -0.0000

Data Index: 571046 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.4333. Min Act: -0.0000

Data Index: 579329 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2616. Min Act: -0.0000

Data Index: 576572 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1246441 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1067493 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.1906. Min Act: -0.0000

Data Index: 163964 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1112922 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.1329. Min Act: -0.0000

Data Index: 384893 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.0643. Min Act: -0.0000

Data Index: 703126 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.0690. Min Act: -0.0000

Data Index: 774716 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1145462 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.0897. Min Act: -0.0000

Data Index: 679004 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.1137. Min Act: -0.0000

Data Index: 717303 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.6351. Min Range: -1.6351

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1196247 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.6351. Min Range: -1.6351

Max Act: 0.9943. Min Act: -0.0000

Data Index: 724277 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 1.6351. Min Range: -1.6351

Max Act: 1.0766. Min Act: -0.0000

Data Index: 228629 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.6351. Min Range: -1.6351

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1581917 (Python Code)

Max Activating Token Index: 842