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

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

Neuron 519 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.4272. Min Act: -0.0000

Data Index: 1008733 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.4117. Min Act: -0.0000

Data Index: 1279026 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.3974. Min Act: -0.0000

Data Index: 552341 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.3015. Min Act: -0.0000

Data Index: 561806 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.3666. Min Act: -0.0000

Data Index: 6718 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.3373. Min Act: -0.0000

Data Index: 1170494 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.1891. Min Act: -0.0000

Data Index: 985968 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.2773. Min Act: -0.0000

Data Index: 432830 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.1775. Min Act: -0.0000

Data Index: 220931 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.2746. Min Act: -0.0000

Data Index: 864754 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.2619. Min Act: -0.0000

Data Index: 1225647 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.2717. Min Act: -0.0000

Data Index: 215246 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.2707. Min Act: -0.0000

Data Index: 683040 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.1535. Min Act: -0.0000

Data Index: 939554 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.0873. Min Act: -0.0000

Data Index: 968059 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.0676. Min Act: -0.0000

Data Index: 900328 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.2964. Min Act: -0.0000

Data Index: 802222 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.2850. Min Act: -0.0000

Data Index: 1089115 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.1683. Min Act: -0.0000

Data Index: 879344 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 2.4272. Min Range: -2.4272

Max Act: 2.0437. Min Act: -0.0000

Data Index: 307189 (C4 (Web Text))

Max Activating Token Index: 820