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

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

Neuron 270 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: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0003

Data Index: 573522 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0785. Min Act: -0.0003

Data Index: 223717 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0800. Min Act: -0.0003

Data Index: 1282594 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0755. Min Act: -0.0003

Data Index: 211816 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1343960 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0723. Min Act: -0.0003

Data Index: 226837 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1250425 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0704. Min Act: -0.0003

Data Index: 37111 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0662. Min Act: -0.0003

Data Index: 1193965 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1016116 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0696. Min Act: -0.0003

Data Index: 315353 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0665. Min Act: -0.0003

Data Index: 196146 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0686. Min Act: -0.0002

Data Index: 710522 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1303287 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0670. Min Act: -0.0003

Data Index: 1205286 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0667. Min Act: -0.0003

Data Index: 95194 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0667. Min Act: -0.0003

Data Index: 572663 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1233065 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1326324 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0658. Min Act: -0.0003

Data Index: 68620 (C4 (Web Text))

Max Activating Token Index: 161