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

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

Neuron 3452 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4745. Min Act: -0.0000

Data Index: 45669 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1352891 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4989. Min Act: -0.0000

Data Index: 450679 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1185815 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.4419. Min Act: -0.0000

Data Index: 1028964 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3909. Min Act: -0.0000

Data Index: 784228 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3918. Min Act: -0.0000

Data Index: 1156154 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1256034 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3402. Min Act: -0.0000

Data Index: 981021 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.5072. Min Act: -0.0000

Data Index: 469477 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3211. Min Act: -0.0000

Data Index: 513958 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3386. Min Act: -0.0000

Data Index: 445774 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3165. Min Act: -0.0000

Data Index: 564459 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3102. Min Act: -0.0000

Data Index: 149569 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2608. Min Act: -0.0000

Data Index: 661734 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2643. Min Act: -0.0000

Data Index: 525451 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2207. Min Act: -0.0000

Data Index: 1075327 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2619. Min Act: -0.0000

Data Index: 252768 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1296002 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3258. Min Act: -0.0000

Data Index: 1021893 (C4 (Web Text))

Max Activating Token Index: 399