Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 679 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.2078. Min Act: -0.0003

Data Index: 1034397 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1848. Min Act: -0.0004

Data Index: 1067470 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.2138. Min Act: -0.0003

Data Index: 788479 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1738. Min Act: -0.0003

Data Index: 122100 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1786. Min Act: -0.0003

Data Index: 63873 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1791. Min Act: -0.0003

Data Index: 284641 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1858. Min Act: -0.0003

Data Index: 766876 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1788. Min Act: -0.0003

Data Index: 1249049 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1783. Min Act: -0.0003

Data Index: 52848 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1737. Min Act: -0.0003

Data Index: 236384 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1556. Min Act: -0.0003

Data Index: 1223721 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1759. Min Act: -0.0003

Data Index: 1084577 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1616. Min Act: -0.0003

Data Index: 1089805 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1850. Min Act: -0.0003

Data Index: 348635 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1524. Min Act: -0.0003

Data Index: 813242 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1630. Min Act: -0.0003

Data Index: 1109130 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1698. Min Act: -0.0002

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1622. Min Act: -0.0003

Data Index: 1040567 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1488. Min Act: -0.0003

Data Index: 313286 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.2138. Min Range: -0.2138

Max Act: 0.1547. Min Act: -0.0003

Data Index: 204242 (C4 (Web Text))

Max Activating Token Index: 94