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

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

Neuron 5214 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: 0.1260. Min Range: -0.1260

Max Act: 0.1248. Min Act: -0.0002

Data Index: 488042 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1230. Min Act: -0.0002

Data Index: 66322 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1260. Min Act: -0.0002

Data Index: 412105 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1222. Min Act: -0.0002

Data Index: 928868 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1105. Min Act: -0.0002

Data Index: 202632 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1046. Min Act: -0.0002

Data Index: 865804 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1096. Min Act: -0.0002

Data Index: 432083 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1012. Min Act: -0.0002

Data Index: 936880 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1142253 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1015. Min Act: -0.0002

Data Index: 217065 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0998. Min Act: -0.0002

Data Index: 1231533 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0996. Min Act: -0.0002

Data Index: 672835 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1029. Min Act: -0.0002

Data Index: 702341 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1254345 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.1007. Min Act: -0.0002

Data Index: 374868 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0971. Min Act: -0.0002

Data Index: 409416 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0940. Min Act: -0.0002

Data Index: 74552 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0970. Min Act: -0.0002

Data Index: 430448 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1224202 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.1260. Min Range: -0.1260

Max Act: 0.0963. Min Act: -0.0002

Data Index: 328652 (C4 (Web Text))

Max Activating Token Index: 1007