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

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

Neuron 3047 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1664. Min Range: -1.1664

Max Act: 1.1664. Min Act: -0.0000

Data Index: 58350 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 1.1664. Min Range: -1.1664

Max Act: 1.0774. Min Act: -0.0000

Data Index: 67326 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.9748. Min Act: -0.0000

Data Index: 814044 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.8862. Min Act: -0.0000

Data Index: 767391 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.9402. Min Act: -0.0000

Data Index: 117063 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.8232. Min Act: -0.0000

Data Index: 702457 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.8030. Min Act: -0.0000

Data Index: 622753 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7829. Min Act: -0.0000

Data Index: 716500 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1252285 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7639. Min Act: -0.0000

Data Index: 65044 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7166. Min Act: -0.0000

Data Index: 1042918 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7297. Min Act: -0.0000

Data Index: 882861 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.6374. Min Act: -0.0000

Data Index: 273905 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1343511 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1270046 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7578. Min Act: -0.0000

Data Index: 828750 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7512. Min Act: -0.0000

Data Index: 1049461 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.7077. Min Act: -0.0000

Data Index: 209422 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.6838. Min Act: -0.0000

Data Index: 972037 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.1664. Min Range: -1.1664

Max Act: 0.6996. Min Act: -0.0000

Data Index: 301063 (C4 (Web Text))

Max Activating Token Index: 939