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

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

Neuron 3209 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: 0.8886. Min Range: -0.8886

Max Act: 0.8817. Min Act: -0.0000

Data Index: 283041 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1053982 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1278969 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6844. Min Act: -0.0000

Data Index: 845547 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1304821 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6929. Min Act: -0.0000

Data Index: 996947 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6006. Min Act: -0.0000

Data Index: 109613 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6335. Min Act: -0.0000

Data Index: 345014 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.6292. Min Act: -0.0000

Data Index: 576330 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1075308 (C4 (Web Text))

Max Activating Token Index: 562

Text #10

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5435. Min Act: -0.0000

Data Index: 943721 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1064099 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5586. Min Act: -0.0000

Data Index: 637450 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1264011 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5538. Min Act: -0.0000

Data Index: 290831 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5509. Min Act: -0.0000

Data Index: 58876 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5121. Min Act: -0.0000

Data Index: 437727 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5205. Min Act: -0.0000

Data Index: 265128 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5057. Min Act: -0.0000

Data Index: 756940 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.8886. Min Range: -0.8886

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1355363 (C4 (Web Text))

Max Activating Token Index: 568