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

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

Neuron 3281 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: 0.3834. Min Range: -0.3834

Max Act: 0.3834. Min Act: -0.0000

Data Index: 829922 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1004162 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3647. Min Act: -0.0000

Data Index: 231754 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3805. Min Act: -0.0000

Data Index: 1241582 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3793. Min Act: -0.0000

Data Index: 951217 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3671. Min Act: -0.0000

Data Index: 254972 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.2908. Min Act: -0.0000

Data Index: 956624 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1214370 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1082175 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.2032. Min Act: -0.0000

Data Index: 225115 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1144526 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1964. Min Act: -0.0000

Data Index: 516447 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1919. Min Act: -0.0000

Data Index: 468826 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1719. Min Act: -0.0000

Data Index: 114648 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1135608 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1710. Min Act: -0.0000

Data Index: 81595 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1830. Min Act: -0.0000

Data Index: 466271 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1728. Min Act: -0.0000

Data Index: 285770 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1822. Min Act: -0.0000

Data Index: 605501 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 0.3834. Min Range: -0.3834

Max Act: 0.1666. Min Act: -0.0000

Data Index: 1142683 (C4 (Web Text))

Max Activating Token Index: 649