Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 76 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1171. Min Act: -0.0005

Data Index: 615465 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1147. Min Act: -0.0005

Data Index: 1050772 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1189. Min Act: -0.0005

Data Index: 874284 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1043. Min Act: -0.0005

Data Index: 742664 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1124. Min Act: -0.0005

Data Index: 646464 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1085. Min Act: -0.0005

Data Index: 1066121 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1171. Min Act: -0.0005

Data Index: 60159 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1096. Min Act: -0.0005

Data Index: 891311 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1115. Min Act: -0.0005

Data Index: 1253174 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1063. Min Act: -0.0005

Data Index: 1287135 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1153. Min Act: -0.0005

Data Index: 164447 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1067. Min Act: -0.0005

Data Index: 5613 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1103. Min Act: -0.0005

Data Index: 1306250 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1126. Min Act: -0.0005

Data Index: 521707 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1090. Min Act: -0.0005

Data Index: 30905 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1086. Min Act: -0.0005

Data Index: 696597 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1048. Min Act: -0.0005

Data Index: 1221262 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1117. Min Act: -0.0004

Data Index: 332580 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.0985. Min Act: -0.0005

Data Index: 348831 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.1189. Min Range: -0.1189

Max Act: 0.1117. Min Act: -0.0005

Data Index: 517105 (C4 (Web Text))

Max Activating Token Index: 131