Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4409 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1627. Min Range: -4.1627

Max Act: 4.1627. Min Act: -0.0000

Data Index: 894162 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 4.1627. Min Range: -4.1627

Max Act: 4.0009. Min Act: -0.0000

Data Index: 378180 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.4242. Min Act: -0.0000

Data Index: 376479 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.5491. Min Act: -0.0000

Data Index: 387068 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.2993. Min Act: -0.0000

Data Index: 413624 (C4 (Web Text))

Max Activating Token Index: 608

Text #5

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.6353. Min Act: -0.0000

Data Index: 1048774 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.2648. Min Act: -0.0000

Data Index: 291986 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.3803. Min Act: -0.0000

Data Index: 832318 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.3910. Min Act: -0.0000

Data Index: 875009 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.2177. Min Act: -0.0000

Data Index: 1185324 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.3574. Min Act: -0.0000

Data Index: 742898 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.1619. Min Act: -0.0000

Data Index: 1146416 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 4.1627. Min Range: -4.1627

Max Act: 2.6546. Min Act: -0.0000

Data Index: 315395 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.1338. Min Act: -0.0000

Data Index: 895060 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.1247. Min Act: -0.0000

Data Index: 161051 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.0720. Min Act: -0.0000

Data Index: 1058819 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 4.1627. Min Range: -4.1627

Max Act: 2.9942. Min Act: -0.0000

Data Index: 783398 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 4.1627. Min Range: -4.1627

Max Act: 2.9768. Min Act: -0.0000

Data Index: 54675 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 4.1627. Min Range: -4.1627

Max Act: 2.9900. Min Act: -0.0000

Data Index: 857708 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 4.1627. Min Range: -4.1627

Max Act: 3.0725. Min Act: -0.0000

Data Index: 331847 (C4 (Web Text))

Max Activating Token Index: 841