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

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

Neuron 49 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8011. Min Act: -0.0002

Data Index: 244278 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8737. Min Act: -0.0002

Data Index: 1214326 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.7163. Min Act: -0.0002

Data Index: 1277474 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6328. Min Act: -0.0002

Data Index: 827967 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6239. Min Act: -0.0002

Data Index: 974880 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6070. Min Act: -0.0002

Data Index: 707713 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5577. Min Act: -0.0002

Data Index: 478727 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5713. Min Act: -0.0002

Data Index: 39478 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.6056. Min Act: -0.0002

Data Index: 788760 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5712. Min Act: -0.0002

Data Index: 1033987 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5844. Min Act: -0.0002

Data Index: 1103313 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5803. Min Act: -0.0002

Data Index: 61580 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5540. Min Act: -0.0002

Data Index: 444820 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5361. Min Act: -0.0002

Data Index: 379277 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5732. Min Act: -0.0002

Data Index: 842102 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5737. Min Act: -0.0002

Data Index: 967621 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5444. Min Act: -0.0002

Data Index: 1018139 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5218. Min Act: -0.0002

Data Index: 94511 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5642. Min Act: -0.0002

Data Index: 767764 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5689. Min Act: -0.0002

Data Index: 703780 (C4 (Web Text))

Max Activating Token Index: 397