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

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

Neuron 2434 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: 0.1287. Min Range: -0.1287

Max Act: 0.1287. Min Act: -0.0004

Data Index: 184432 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1231. Min Act: -0.0004

Data Index: 193508 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1252. Min Act: -0.0004

Data Index: 405795 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1131. Min Act: -0.0004

Data Index: 1333083 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1077. Min Act: -0.0004

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1187. Min Act: -0.0004

Data Index: 427306 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1095. Min Act: -0.0004

Data Index: 620559 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1126. Min Act: -0.0004

Data Index: 1187969 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1193. Min Act: -0.0004

Data Index: 1252283 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1193. Min Act: -0.0004

Data Index: 1231583 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1027. Min Act: -0.0004

Data Index: 1135450 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1191. Min Act: -0.0004

Data Index: 914908 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1110. Min Act: -0.0004

Data Index: 297178 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1081. Min Act: -0.0004

Data Index: 797543 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1097. Min Act: -0.0004

Data Index: 825564 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1126. Min Act: -0.0004

Data Index: 397629 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1075. Min Act: -0.0004

Data Index: 966736 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1038. Min Act: -0.0004

Data Index: 802668 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1071. Min Act: -0.0004

Data Index: 1242470 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.1287. Min Range: -0.1287

Max Act: 0.1191. Min Act: -0.0004

Data Index: 295269 (C4 (Web Text))

Max Activating Token Index: 925