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

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

Neuron 801 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.7817. Min Act: -0.0001

Data Index: 432219 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.8528. Min Act: -0.0001

Data Index: 927151 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.9569. Min Act: -0.0001

Data Index: 391850 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.8613. Min Act: -0.0001

Data Index: 638483 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.5850. Min Act: -0.0001

Data Index: 288820 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.8774. Min Act: -0.0001

Data Index: 986050 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.7599. Min Act: -0.0001

Data Index: 730905 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.7500. Min Act: -0.0001

Data Index: 339751 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.8450. Min Act: -0.0001

Data Index: 412480 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.9648. Min Act: -0.0001

Data Index: 667933 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.8305. Min Act: -0.0001

Data Index: 721929 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.7421. Min Act: -0.0001

Data Index: 1238185 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.5973. Min Act: -0.0001

Data Index: 1116050 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.6698. Min Act: -0.0001

Data Index: 209960 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.7621. Min Act: -0.0001

Data Index: 1349526 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.6707. Min Act: -0.0001

Data Index: 1272693 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.6356. Min Act: -0.0001

Data Index: 568626 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.4939. Min Act: -0.0001

Data Index: 57592 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.5304. Min Act: -0.0001

Data Index: 1331529 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 1.9648. Min Range: -1.9648

Max Act: 1.4229. Min Act: -0.0001

Data Index: 547581 (C4 (Web Text))

Max Activating Token Index: 294