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

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

Neuron 3585 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0002

Data Index: 1390933 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1203. Min Act: -0.0002

Data Index: 1371924 (Python Code)

Max Activating Token Index: 470

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1246. Min Act: -0.0002

Data Index: 1413949 (Python Code)

Max Activating Token Index: 227

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1137. Min Act: -0.0002

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1549122 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1174. Min Act: -0.0002

Data Index: 3222 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1431153 (Python Code)

Max Activating Token Index: 827

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1593791 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1130. Min Act: -0.0002

Data Index: 1511120 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1161. Min Act: -0.0002

Data Index: 1606842 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1561614 (Python Code)

Max Activating Token Index: 1009

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1039. Min Act: -0.0002

Data Index: 1603106 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1399831 (Python Code)

Max Activating Token Index: 221

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1069. Min Act: -0.0002

Data Index: 558562 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1425160 (Python Code)

Max Activating Token Index: 969

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1413250 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1592650 (Python Code)

Max Activating Token Index: 359

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1321527 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1078. Min Act: -0.0002

Data Index: 602439 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1072. Min Act: -0.0002

Data Index: 427983 (C4 (Web Text))

Max Activating Token Index: 724