Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1643 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0938. Min Act: -0.0002

Data Index: 220275 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1645871 (Python Code)

Max Activating Token Index: 70

Text #2

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0854. Min Act: -0.0003

Data Index: 1387437 (Python Code)

Max Activating Token Index: 66

Text #3

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0799. Min Act: -0.0003

Data Index: 1208476 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0834. Min Act: -0.0003

Data Index: 1592661 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0802. Min Act: -0.0003

Data Index: 1457022 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0783. Min Act: -0.0003

Data Index: 1445224 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1578803 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1374917 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0757. Min Act: -0.0003

Data Index: 1551632 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1541029 (Python Code)

Max Activating Token Index: 135

Text #11

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1459000 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0764. Min Act: -0.0003

Data Index: 1601022 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1513576 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0757. Min Act: -0.0003

Data Index: 1483633 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0708. Min Act: -0.0002

Data Index: 483722 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0720. Min Act: -0.0003

Data Index: 1478357 (Python Code)

Max Activating Token Index: 116

Text #17

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0702. Min Act: -0.0002

Data Index: 812768 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1583656 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 0.0938. Min Range: -0.0938

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1539002 (Python Code)

Max Activating Token Index: 36