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

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

Neuron 1886 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.4826. Min Act: -0.0000

Data Index: 725973 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.2475. Min Act: -0.0000

Data Index: 1030860 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.1914. Min Act: -0.0000

Data Index: 667263 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.1243. Min Act: -0.0000

Data Index: 630069 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.0503. Min Act: -0.0000

Data Index: 436496 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.1806. Min Act: -0.0000

Data Index: 1299798 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.0363. Min Act: -0.0000

Data Index: 257839 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.0828. Min Act: -0.0000

Data Index: 115293 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.9612. Min Act: -0.0000

Data Index: 484902 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.9503. Min Act: -0.0000

Data Index: 433188 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.9581. Min Act: -0.0000

Data Index: 950477 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.0546. Min Act: -0.0000

Data Index: 1170908 (C4 (Web Text))

Max Activating Token Index: 580

Text #12

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.9371. Min Act: -0.0000

Data Index: 924418 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.9329. Min Act: -0.0000

Data Index: 939072 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 2.4826. Min Range: -2.4826

Max Act: 2.0170. Min Act: -0.0000

Data Index: 98646 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.9013. Min Act: -0.0000

Data Index: 42913 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.7084. Min Act: -0.0000

Data Index: 765533 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.6747. Min Act: -0.0000

Data Index: 1109200 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.8629. Min Act: -0.0000

Data Index: 1292058 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 2.4826. Min Range: -2.4826

Max Act: 1.7550. Min Act: -0.0000

Data Index: 123900 (C4 (Web Text))

Max Activating Token Index: 603