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

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

Neuron 1992 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.3783. Min Act: -0.0001

Data Index: 396167 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2402. Min Act: -0.0001

Data Index: 358891 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2505. Min Act: -0.0001

Data Index: 319225 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2185. Min Act: -0.0001

Data Index: 811253 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2220. Min Act: -0.0000

Data Index: 509032 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1954. Min Act: -0.0001

Data Index: 750840 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.2106. Min Act: -0.0000

Data Index: 543846 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1882. Min Act: -0.0001

Data Index: 118072 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1898. Min Act: -0.0001

Data Index: 633631 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1877. Min Act: -0.0000

Data Index: 524932 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1819. Min Act: -0.0001

Data Index: 1338648 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1929. Min Act: -0.0000

Data Index: 814535 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1285824 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1932. Min Act: -0.0001

Data Index: 535298 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1842. Min Act: -0.0001

Data Index: 670001 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1062220 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1824. Min Act: -0.0001

Data Index: 813581 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1344147 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1863. Min Act: -0.0001

Data Index: 237569 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.3783. Min Range: -0.3783

Max Act: 0.1599. Min Act: -0.0000

Data Index: 340798 (C4 (Web Text))

Max Activating Token Index: 773