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

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

Neuron 2650 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2574. Min Act: -0.0001

Data Index: 274858 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2556. Min Act: -0.0001

Data Index: 769526 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2302. Min Act: -0.0001

Data Index: 96811 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2071. Min Act: -0.0001

Data Index: 775019 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2132. Min Act: -0.0001

Data Index: 714051 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2302. Min Act: -0.0001

Data Index: 987373 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2174. Min Act: -0.0001

Data Index: 653500 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1989. Min Act: -0.0001

Data Index: 878835 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2009. Min Act: -0.0001

Data Index: 404216 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1546. Min Act: -0.0001

Data Index: 9636 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1863. Min Act: -0.0001

Data Index: 529372 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1791. Min Act: -0.0001

Data Index: 709889 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1919. Min Act: -0.0001

Data Index: 685790 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1191379 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1144405 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1808. Min Act: -0.0001

Data Index: 572178 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1085721 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1063329 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1779. Min Act: -0.0001

Data Index: 322529 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1792. Min Act: -0.0001

Data Index: 991107 (C4 (Web Text))

Max Activating Token Index: 369