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

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

Neuron 4346 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: 0.1323. Min Range: -0.1323

Max Act: 0.1323. Min Act: -0.0002

Data Index: 203176 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1235. Min Act: -0.0002

Data Index: 1317027 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1009355 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1016949 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1243761 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1167. Min Act: -0.0002

Data Index: 527241 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1080. Min Act: -0.0002

Data Index: 479362 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1086. Min Act: -0.0002

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1349240 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1106. Min Act: -0.0002

Data Index: 198408 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1067. Min Act: -0.0002

Data Index: 1044906 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1240934 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1185. Min Act: -0.0002

Data Index: 1073631 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1140066 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1092. Min Act: -0.0002

Data Index: 74548 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1242935 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1092. Min Act: -0.0002

Data Index: 561721 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1035. Min Act: -0.0002

Data Index: 1062076 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1038059 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1061. Min Act: -0.0002

Data Index: 15162 (C4 (Web Text))

Max Activating Token Index: 86