Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 480 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2856. Min Act: -0.0000

Data Index: 182187 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0000

Data Index: 257801 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2564. Min Act: -0.0000

Data Index: 327986 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1040976 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1557549 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2058. Min Act: -0.0000

Data Index: 202139 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2134. Min Act: -0.0000

Data Index: 1289355 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2046. Min Act: -0.0000

Data Index: 136628 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2233. Min Act: -0.0000

Data Index: 243067 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1300245 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2012. Min Act: -0.0000

Data Index: 859951 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1992. Min Act: -0.0000

Data Index: 482369 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2070. Min Act: -0.0000

Data Index: 6031 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1954. Min Act: -0.0000

Data Index: 278884 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1329353 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1177874 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1828. Min Act: -0.0000

Data Index: 362743 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2111. Min Act: -0.0000

Data Index: 507249 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1851. Min Act: -0.0000

Data Index: 624152 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1578623 (Python Code)

Max Activating Token Index: 422