Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1891 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.1009. Min Act: -0.0002

Data Index: 724453 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.1009. Min Act: -0.0002

Data Index: 558941 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0929. Min Act: -0.0002

Data Index: 938281 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1315431 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0761. Min Act: -0.0002

Data Index: 260162 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0811. Min Act: -0.0002

Data Index: 691687 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1030485 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1155645 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0809. Min Act: -0.0002

Data Index: 523984 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0810. Min Act: -0.0001

Data Index: 285888 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1215406 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0805. Min Act: -0.0002

Data Index: 146199 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0804. Min Act: -0.0002

Data Index: 967792 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0811. Min Act: -0.0002

Data Index: 282524 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1316889 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1282822 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0789. Min Act: -0.0001

Data Index: 482706 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1303034 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0753. Min Act: -0.0002

Data Index: 199441 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.1009. Min Range: -0.1009

Max Act: 0.0784. Min Act: -0.0002

Data Index: 873051 (C4 (Web Text))

Max Activating Token Index: 966