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

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

Neuron 3157 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1224. Min Act: -0.0001

Data Index: 416216 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1126. Min Act: 0.0000

Data Index: 1325743 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1027915 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1138. Min Act: -0.0000

Data Index: 1125550 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1156. Min Act: -0.0000

Data Index: 984129 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1126. Min Act: -0.0001

Data Index: 535501 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1081. Min Act: -0.0001

Data Index: 803042 (C4 (Web Text))

Max Activating Token Index: 460

Text #7

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1102. Min Act: -0.0001

Data Index: 564906 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1095. Min Act: -0.0000

Data Index: 851980 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1054. Min Act: -0.0001

Data Index: 127542 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1049. Min Act: -0.0001

Data Index: 341976 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1189631 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1067. Min Act: -0.0000

Data Index: 351082 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1064. Min Act: -0.0000

Data Index: 817774 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1029. Min Act: -0.0000

Data Index: 366128 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1056374 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1062. Min Act: -0.0000

Data Index: 297357 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1046. Min Act: -0.0001

Data Index: 335425 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1015. Min Act: -0.0001

Data Index: 498188 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.1224. Min Range: -0.1224

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1161420 (C4 (Web Text))

Max Activating Token Index: 949