Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 236 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1172. Min Act: -0.0002

Data Index: 236820 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0999. Min Act: -0.0001

Data Index: 501675 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0873. Min Act: -0.0002

Data Index: 738024 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.1017. Min Act: -0.0002

Data Index: 208453 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0837. Min Act: -0.0002

Data Index: 7501 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0820. Min Act: -0.0002

Data Index: 736682 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0872. Min Act: -0.0002

Data Index: 736079 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0854. Min Act: -0.0002

Data Index: 382998 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0780. Min Act: -0.0002

Data Index: 911314 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0803. Min Act: -0.0002

Data Index: 599419 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0804. Min Act: -0.0002

Data Index: 618024 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1126238 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1301376 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0839. Min Act: -0.0001

Data Index: 247581 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0795. Min Act: -0.0002

Data Index: 705898 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0815. Min Act: -0.0002

Data Index: 651829 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0793. Min Act: -0.0002

Data Index: 743432 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1216923 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0792. Min Act: -0.0001

Data Index: 904667 (C4 (Web Text))

Max Activating Token Index: 149

Text #19

Max Range: 0.1172. Min Range: -0.1172

Max Act: 0.0788. Min Act: -0.0001

Data Index: 377901 (C4 (Web Text))

Max Activating Token Index: 192