Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2986 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1278. Min Act: -0.0001

Data Index: 464144 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1239. Min Act: -0.0001

Data Index: 1256983 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1185. Min Act: -0.0001

Data Index: 361282 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1136. Min Act: -0.0001

Data Index: 843225 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1319914 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1177. Min Act: -0.0001

Data Index: 141286 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1122. Min Act: -0.0001

Data Index: 239232 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1148. Min Act: -0.0001

Data Index: 765512 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1108126 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1097453 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1089. Min Act: -0.0001

Data Index: 897075 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1324753 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1035. Min Act: -0.0001

Data Index: 885379 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1031. Min Act: -0.0001

Data Index: 77375 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1016. Min Act: -0.0001

Data Index: 348318 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1012. Min Act: -0.0001

Data Index: 185927 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1058. Min Act: -0.0001

Data Index: 528625 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1090. Min Act: -0.0001

Data Index: 760143 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1056. Min Act: -0.0001

Data Index: 96711 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1010. Min Act: -0.0001

Data Index: 764493 (C4 (Web Text))

Max Activating Token Index: 576