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

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

Neuron 2238 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1279. Min Act: -0.0002

Data Index: 629064 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1208. Min Act: -0.0002

Data Index: 6824 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1201. Min Act: -0.0002

Data Index: 926548 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1189. Min Act: -0.0002

Data Index: 880427 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1185. Min Act: -0.0002

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1162. Min Act: -0.0002

Data Index: 481974 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1155. Min Act: -0.0002

Data Index: 843925 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1326037 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1091. Min Act: -0.0002

Data Index: 782587 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1084. Min Act: -0.0002

Data Index: 21037 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1074. Min Act: -0.0002

Data Index: 614747 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1055. Min Act: -0.0002

Data Index: 210358 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1054. Min Act: -0.0002

Data Index: 829022 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1102529 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1077539 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1163525 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1278245 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1184006 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1104215 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.1279. Min Range: -0.1279

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1278629 (C4 (Web Text))

Max Activating Token Index: 100