Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2650 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0914. Min Act: -0.0002

Data Index: 207289 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1095730 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0798. Min Act: -0.0002

Data Index: 598776 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1287273 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0779. Min Act: -0.0002

Data Index: 133776 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0746. Min Act: -0.0002

Data Index: 932670 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0760. Min Act: -0.0002

Data Index: 738348 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0716. Min Act: -0.0002

Data Index: 13456 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1182095 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1243546 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1242701 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1267458 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0683. Min Act: -0.0002

Data Index: 871139 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0680. Min Act: -0.0002

Data Index: 417939 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0679. Min Act: -0.0002

Data Index: 441068 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0646. Min Act: -0.0002

Data Index: 574489 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0661. Min Act: -0.0002

Data Index: 373132 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1056743 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1002056 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0627. Min Act: -0.0002

Data Index: 746950 (C4 (Web Text))

Max Activating Token Index: 85