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

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

Neuron 4314 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7986. Min Act: -0.0002

Data Index: 504978 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7994. Min Act: -0.0002

Data Index: 839424 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7732. Min Act: -0.0002

Data Index: 295355 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7398. Min Act: -0.0002

Data Index: 330206 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7207. Min Act: -0.0002

Data Index: 315373 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7199. Min Act: -0.0002

Data Index: 916521 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7179. Min Act: -0.0002

Data Index: 835037 (C4 (Web Text))

Max Activating Token Index: 572

Text #7

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6712. Min Act: -0.0002

Data Index: 398231 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7173. Min Act: -0.0002

Data Index: 1225945 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.7187. Min Act: -0.0002

Data Index: 1256517 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6891. Min Act: -0.0002

Data Index: 804524 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6582. Min Act: -0.0002

Data Index: 385472 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6664. Min Act: -0.0002

Data Index: 401689 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6438. Min Act: -0.0002

Data Index: 612201 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6590. Min Act: -0.0002

Data Index: 642757 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6603. Min Act: -0.0002

Data Index: 529014 (C4 (Web Text))

Max Activating Token Index: 95

Text #16

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6326. Min Act: -0.0002

Data Index: 223151 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6727. Min Act: -0.0002

Data Index: 1075398 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6665. Min Act: -0.0002

Data Index: 1097379 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.7994. Min Range: -0.7994

Max Act: 0.6148. Min Act: -0.0002

Data Index: 519621 (C4 (Web Text))

Max Activating Token Index: 10