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

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

Neuron 843 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0002

Data Index: 644323 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0918. Min Act: -0.0002

Data Index: 127498 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1542234 (Python Code)

Max Activating Token Index: 84

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1357911 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0759. Min Act: -0.0002

Data Index: 214028 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1343902 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0732. Min Act: -0.0002

Data Index: 267897 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1641054 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0718. Min Act: -0.0002

Data Index: 504938 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1330952 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1524116 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1106162 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0689. Min Act: -0.0002

Data Index: 250325 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0685. Min Act: -0.0001

Data Index: 1496002 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1381921 (Python Code)

Max Activating Token Index: 875

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0675. Min Act: -0.0002

Data Index: 19279 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1617060 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1076765 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1404899 (Python Code)

Max Activating Token Index: 750

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1425447 (Python Code)

Max Activating Token Index: 887