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

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

Neuron 3429 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.7623. Min Act: -0.0000

Data Index: 347325 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2840. Min Act: -0.0000

Data Index: 656332 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.4400. Min Act: -0.0000

Data Index: 855804 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2921. Min Act: -0.0000

Data Index: 288730 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.3419. Min Act: -0.0000

Data Index: 620007 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2815. Min Act: -0.0000

Data Index: 1047174 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2625. Min Act: -0.0000

Data Index: 1050837 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.3053. Min Act: -0.0000

Data Index: 772774 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2034. Min Act: -0.0000

Data Index: 746515 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2855. Min Act: -0.0000

Data Index: 512115 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2321. Min Act: -0.0000

Data Index: 138555 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.1702. Min Act: -0.0000

Data Index: 797040 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.1682. Min Act: -0.0000

Data Index: 693817 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 1.7623. Min Range: -1.7623

Max Act: 0.9943. Min Act: -0.0001

Data Index: 55352 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1354073 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2529. Min Act: -0.0000

Data Index: 886852 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.2254. Min Act: -0.0000

Data Index: 177826 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1126567 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.1656. Min Act: -0.0000

Data Index: 242298 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.7623. Min Range: -1.7623

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1311728 (C4 (Web Text))

Max Activating Token Index: 226