Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1536 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0001

Data Index: 370288 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1154. Min Act: -0.0002

Data Index: 719182 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1180. Min Act: -0.0002

Data Index: 172758 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1172. Min Act: -0.0002

Data Index: 347541 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1166. Min Act: -0.0002

Data Index: 548173 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1187. Min Act: -0.0002

Data Index: 977201 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1085470 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1323135 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1147. Min Act: -0.0001

Data Index: 740038 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1342379 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1123. Min Act: -0.0002

Data Index: 655974 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1028. Min Act: -0.0001

Data Index: 716694 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1018944 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1039. Min Act: -0.0002

Data Index: 37977 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1036. Min Act: -0.0002

Data Index: 871060 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1055. Min Act: -0.0001

Data Index: 769491 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.0983. Min Act: -0.0002

Data Index: 475726 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1095. Min Act: -0.0002

Data Index: 850699 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1088. Min Act: -0.0002

Data Index: 364353 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1215183 (C4 (Web Text))

Max Activating Token Index: 323