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

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

Neuron 98 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: 2.2606. Min Range: -2.2606

Max Act: 2.2149. Min Act: -0.0000

Data Index: 817904 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 2.2606. Min Range: -2.2606

Max Act: 2.2606. Min Act: -0.0000

Data Index: 1133024 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 2.2606. Min Range: -2.2606

Max Act: 2.0911. Min Act: -0.0000

Data Index: 122765 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 2.2606. Min Range: -2.2606

Max Act: 2.1521. Min Act: -0.0000

Data Index: 1025016 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 2.2606. Min Range: -2.2606

Max Act: 2.1811. Min Act: -0.0000

Data Index: 735172 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 2.2606. Min Range: -2.2606

Max Act: 2.0441. Min Act: -0.0000

Data Index: 334583 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.9842. Min Act: -0.0000

Data Index: 814912 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.7682. Min Act: -0.0000

Data Index: 1078322 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.8327. Min Act: -0.0000

Data Index: 364340 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.9150. Min Act: -0.0000

Data Index: 813372 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.9106. Min Act: -0.0000

Data Index: 1625358 (Python Code)

Max Activating Token Index: 527

Text #11

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.8030. Min Act: -0.0000

Data Index: 82540 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.9764. Min Act: -0.0000

Data Index: 1613391 (Python Code)

Max Activating Token Index: 344

Text #13

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.9382. Min Act: -0.0000

Data Index: 206858 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.7230. Min Act: -0.0000

Data Index: 498769 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 2.2606. Min Range: -2.2606

Max Act: 2.1279. Min Act: -0.0000

Data Index: 715277 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.7902. Min Act: -0.0000

Data Index: 755046 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.7919. Min Act: -0.0000

Data Index: 987555 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.8905. Min Act: -0.0000

Data Index: 1288315 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 2.2606. Min Range: -2.2606

Max Act: 1.7699. Min Act: -0.0000

Data Index: 660413 (C4 (Web Text))

Max Activating Token Index: 596