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

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

Neuron 3135 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0745. Min Range: -1.0745

Max Act: 1.0745. Min Act: -0.0000

Data Index: 267858 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.0745. Min Range: -1.0745

Max Act: 1.0064. Min Act: -0.0000

Data Index: 674236 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.9538. Min Act: -0.0000

Data Index: 635711 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.9664. Min Act: -0.0000

Data Index: 969463 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1147397 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.9104. Min Act: -0.0000

Data Index: 252104 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1378432 (Python Code)

Max Activating Token Index: 839

Text #7

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1552033 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.8018. Min Act: -0.0000

Data Index: 270213 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.7873. Min Act: -0.0000

Data Index: 862493 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.7102. Min Act: -0.0000

Data Index: 885870 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.8024. Min Act: -0.0000

Data Index: 20250 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.7185. Min Act: -0.0000

Data Index: 969264 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.7851. Min Act: -0.0000

Data Index: 488770 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.6823. Min Act: -0.0000

Data Index: 129192 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.6973. Min Act: -0.0000

Data Index: 258362 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1641568 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.6852. Min Act: -0.0000

Data Index: 1030559 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.7482. Min Act: -0.0000

Data Index: 388881 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.0745. Min Range: -1.0745

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1642768 (Python Code)

Max Activating Token Index: 999