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

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

Neuron 1698 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2195. Min Act: -0.0001

Data Index: 952077 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2433. Min Act: -0.0001

Data Index: 1074121 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1200666 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2067. Min Act: -0.0001

Data Index: 234996 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2051. Min Act: -0.0001

Data Index: 589587 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2084. Min Act: -0.0001

Data Index: 456425 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1941. Min Act: -0.0001

Data Index: 415050 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1930. Min Act: -0.0001

Data Index: 389646 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1814. Min Act: -0.0001

Data Index: 1048515 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1829. Min Act: -0.0001

Data Index: 1215942 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1756. Min Act: -0.0001

Data Index: 219807 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.2011. Min Act: -0.0001

Data Index: 865637 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1890. Min Act: -0.0001

Data Index: 920114 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1042782 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1711. Min Act: -0.0001

Data Index: 281114 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1822. Min Act: -0.0001

Data Index: 405303 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1767. Min Act: -0.0001

Data Index: 907880 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1312274 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1712. Min Act: -0.0001

Data Index: 508542 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.2433. Min Range: -0.2433

Max Act: 0.1838. Min Act: -0.0001

Data Index: 484438 (C4 (Web Text))

Max Activating Token Index: 57