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

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

Neuron 1639 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.3180. Min Act: -0.0000

Data Index: 41092 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2969. Min Act: -0.0000

Data Index: 869990 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1097556 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2431. Min Act: -0.0000

Data Index: 328944 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1021219 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2265. Min Act: -0.0000

Data Index: 404540 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2219. Min Act: -0.0000

Data Index: 237439 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2208. Min Act: -0.0000

Data Index: 353655 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2371. Min Act: -0.0000

Data Index: 561585 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2157. Min Act: -0.0000

Data Index: 508237 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2239. Min Act: -0.0000

Data Index: 974807 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2144. Min Act: -0.0000

Data Index: 956089 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2205. Min Act: -0.0000

Data Index: 19662 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2051. Min Act: -0.0000

Data Index: 706853 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1115976 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2063. Min Act: -0.0000

Data Index: 195292 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2105. Min Act: -0.0000

Data Index: 23581 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.1966. Min Act: -0.0000

Data Index: 665861 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.1972. Min Act: -0.0000

Data Index: 726776 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.3180. Min Range: -0.3180

Max Act: 0.2049. Min Act: -0.0000

Data Index: 46335 (C4 (Web Text))

Max Activating Token Index: 142