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

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

Neuron 5030 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: 0.1058. Min Range: -0.1058

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1580906 (Python Code)

Max Activating Token Index: 727

Text #1

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1601234 (Python Code)

Max Activating Token Index: 368

Text #2

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1614683 (Python Code)

Max Activating Token Index: 76

Text #3

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0704. Min Act: -0.0002

Data Index: 244862 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1569648 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1388810 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0737. Min Act: -0.0002

Data Index: 624543 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1463585 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1453268 (Python Code)

Max Activating Token Index: 566

Text #9

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0726. Min Act: -0.0002

Data Index: 574574 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0742. Min Act: -0.0002

Data Index: 966200 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1428617 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1481460 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1413477 (Python Code)

Max Activating Token Index: 507

Text #14

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1469593 (Python Code)

Max Activating Token Index: 1019

Text #15

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0703. Min Act: -0.0002

Data Index: 443134 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0656. Min Act: -0.0002

Data Index: 819947 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0679. Min Act: -0.0002

Data Index: 90834 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0725. Min Act: -0.0002

Data Index: 38728 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.1058. Min Range: -0.1058

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1550247 (Python Code)

Max Activating Token Index: 654