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

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

Neuron 633 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1142. Min Act: -0.0004

Data Index: 1315660 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1170. Min Act: -0.0004

Data Index: 166986 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1091. Min Act: -0.0004

Data Index: 1330217 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1085. Min Act: -0.0004

Data Index: 531824 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1208. Min Act: -0.0004

Data Index: 1246254 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1157. Min Act: -0.0004

Data Index: 1151098 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1070. Min Act: -0.0004

Data Index: 1179669 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1087. Min Act: -0.0004

Data Index: 560101 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1085. Min Act: -0.0004

Data Index: 604092 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1086. Min Act: -0.0004

Data Index: 155911 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1167. Min Act: -0.0004

Data Index: 759071 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1150. Min Act: -0.0004

Data Index: 144917 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1212. Min Act: -0.0004

Data Index: 579650 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1086. Min Act: -0.0004

Data Index: 475451 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1083. Min Act: -0.0004

Data Index: 969592 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1080. Min Act: -0.0004

Data Index: 455163 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1033. Min Act: -0.0004

Data Index: 1274727 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0924. Min Act: -0.0004

Data Index: 59097 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.1065. Min Act: -0.0004

Data Index: 959601 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.1212. Min Range: -0.1212

Max Act: 0.0991. Min Act: -0.0004

Data Index: 1288937 (C4 (Web Text))

Max Activating Token Index: 154