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

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

Neuron 3930 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: 2.0648. Min Range: -2.0648

Max Act: 2.0053. Min Act: -0.0000

Data Index: 1452684 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 2.0648. Min Range: -2.0648

Max Act: 2.0015. Min Act: -0.0000

Data Index: 1619154 (Python Code)

Max Activating Token Index: 857

Text #2

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.8743. Min Act: -0.0000

Data Index: 1468909 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.8456. Min Act: -0.0000

Data Index: 1587696 (Python Code)

Max Activating Token Index: 228

Text #4

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.9106. Min Act: -0.0000

Data Index: 1382187 (Python Code)

Max Activating Token Index: 662

Text #5

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.9155. Min Act: -0.0000

Data Index: 1415845 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.9060. Min Act: -0.0000

Data Index: 1584523 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.8860. Min Act: -0.0000

Data Index: 1535188 (Python Code)

Max Activating Token Index: 735

Text #8

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.6825. Min Act: -0.0000

Data Index: 1395360 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.9882. Min Act: -0.0000

Data Index: 1384972 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.8954. Min Act: -0.0000

Data Index: 1486590 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.7570. Min Act: -0.0000

Data Index: 1463429 (Python Code)

Max Activating Token Index: 672

Text #12

Max Range: 2.0648. Min Range: -2.0648

Max Act: 2.0648. Min Act: -0.0000

Data Index: 1519805 (Python Code)

Max Activating Token Index: 783

Text #13

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.7572. Min Act: -0.0000

Data Index: 1530386 (Python Code)

Max Activating Token Index: 864

Text #14

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.8125. Min Act: -0.0000

Data Index: 1364721 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.7789. Min Act: -0.0000

Data Index: 1387969 (Python Code)

Max Activating Token Index: 350

Text #16

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.8897. Min Act: -0.0000

Data Index: 1559838 (Python Code)

Max Activating Token Index: 896

Text #17

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1499665 (Python Code)

Max Activating Token Index: 601

Text #18

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.8011. Min Act: -0.0000

Data Index: 1398856 (Python Code)

Max Activating Token Index: 313

Text #19

Max Range: 2.0648. Min Range: -2.0648

Max Act: 1.8725. Min Act: -0.0000

Data Index: 1405113 (Python Code)

Max Activating Token Index: 909