Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1416 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1044065 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1194672 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0784. Min Act: -0.0001

Data Index: 42861 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0741. Min Act: -0.0002

Data Index: 827703 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0756. Min Act: -0.0001

Data Index: 1083003 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0738. Min Act: -0.0002

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0720. Min Act: -0.0001

Data Index: 215562 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0677. Min Act: -0.0002

Data Index: 962988 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0688. Min Act: -0.0001

Data Index: 598047 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0682. Min Act: -0.0001

Data Index: 471881 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0695. Min Act: -0.0002

Data Index: 475029 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0645. Min Act: -0.0001

Data Index: 749859 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0660. Min Act: -0.0002

Data Index: 697851 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0657. Min Act: -0.0002

Data Index: 708547 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1319538 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1228345 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0609. Min Act: -0.0001

Data Index: 999073 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0589. Min Act: -0.0001

Data Index: 89510 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0633. Min Act: -0.0001

Data Index: 755593 (C4 (Web Text))

Max Activating Token Index: 46