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

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

Neuron 894 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: 0.1006. Min Range: -0.1006

Max Act: 0.1006. Min Act: -0.0003

Data Index: 173171 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0912. Min Act: -0.0004

Data Index: 834044 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0786. Min Act: -0.0003

Data Index: 118092 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1159171 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1140339 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1262815 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1293692 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0642. Min Act: -0.0003

Data Index: 103623 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0667. Min Act: -0.0004

Data Index: 390337 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0659. Min Act: -0.0004

Data Index: 953550 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0646. Min Act: -0.0003

Data Index: 279818 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0620. Min Act: -0.0003

Data Index: 62842 (C4 (Web Text))

Max Activating Token Index: 613

Text #12

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0609. Min Act: -0.0003

Data Index: 833130 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0641. Min Act: -0.0003

Data Index: 750108 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0660. Min Act: -0.0004

Data Index: 1172909 (C4 (Web Text))

Max Activating Token Index: 764

Text #15

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0606. Min Act: -0.0003

Data Index: 703590 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0630. Min Act: -0.0003

Data Index: 910965 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0621. Min Act: -0.0003

Data Index: 487764 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0597. Min Act: -0.0004

Data Index: 907237 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0643. Min Act: -0.0003

Data Index: 574326 (C4 (Web Text))

Max Activating Token Index: 788