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

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

Neuron 1391 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.2616. Min Act: -0.0000

Data Index: 865966 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.2532. Min Act: -0.0001

Data Index: 917055 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1993. Min Act: -0.0000

Data Index: 53067 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1912. Min Act: -0.0001

Data Index: 518822 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1830. Min Act: -0.0000

Data Index: 996681 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1934. Min Act: -0.0001

Data Index: 126653 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1843. Min Act: -0.0001

Data Index: 987294 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1812. Min Act: -0.0001

Data Index: 436198 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1852. Min Act: -0.0000

Data Index: 281884 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1836. Min Act: -0.0001

Data Index: 460730 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1837. Min Act: -0.0001

Data Index: 36184 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1777. Min Act: -0.0001

Data Index: 542932 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1602. Min Act: -0.0001

Data Index: 519906 (C4 (Web Text))

Max Activating Token Index: 704

Text #13

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1034783 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1862. Min Act: -0.0001

Data Index: 8937 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1141256 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1683. Min Act: -0.0001

Data Index: 36303 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1762. Min Act: -0.0001

Data Index: 784591 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1685. Min Act: -0.0001

Data Index: 134876 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1680. Min Act: -0.0001

Data Index: 724535 (C4 (Web Text))

Max Activating Token Index: 628