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

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

Neuron 4832 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0746. Min Act: -0.0002

Data Index: 837861 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0704. Min Act: -0.0002

Data Index: 837332 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1351852 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0643. Min Act: -0.0002

Data Index: 800466 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0619. Min Act: -0.0002

Data Index: 784664 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0630. Min Act: -0.0002

Data Index: 423554 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0619. Min Act: -0.0002

Data Index: 93629 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0595. Min Act: -0.0002

Data Index: 223611 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0556. Min Act: -0.0002

Data Index: 725179 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0555. Min Act: -0.0002

Data Index: 108532 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0545. Min Act: -0.0002

Data Index: 286897 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0538. Min Act: -0.0002

Data Index: 35857 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1164015 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1312151 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0529. Min Act: -0.0002

Data Index: 571292 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0533. Min Act: -0.0002

Data Index: 566558 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1023861 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1048866 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1345841 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1272395 (C4 (Web Text))

Max Activating Token Index: 528