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

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

Neuron 4463 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2759. Min Act: -0.0000

Data Index: 442972 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2612. Min Act: -0.0000

Data Index: 230963 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2213. Min Act: 0.0000

Data Index: 45424 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2205. Min Act: -0.0000

Data Index: 503456 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2206. Min Act: -0.0000

Data Index: 714340 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2282. Min Act: -0.0000

Data Index: 703826 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1252433 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1998. Min Act: -0.0000

Data Index: 711982 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2058. Min Act: -0.0000

Data Index: 758782 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1893. Min Act: -0.0000

Data Index: 960452 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1947. Min Act: -0.0000

Data Index: 675003 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1220174 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1921. Min Act: -0.0000

Data Index: 306577 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1822. Min Act: -0.0000

Data Index: 13705 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1112055 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1858. Min Act: -0.0000

Data Index: 1231015 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1781. Min Act: -0.0000

Data Index: 651874 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1004020 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1718. Min Act: -0.0000

Data Index: 857499 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.2759. Min Range: -0.2759

Max Act: 0.1765. Min Act: -0.0000

Data Index: 72872 (C4 (Web Text))

Max Activating Token Index: 868