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

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

Neuron 740 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1063843 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1106989 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1208. Min Act: -0.0002

Data Index: 1062193 (C4 (Web Text))

Max Activating Token Index: 719

Text #3

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1035. Min Act: -0.0002

Data Index: 34469 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1181. Min Act: -0.0002

Data Index: 79421 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1205. Min Act: -0.0002

Data Index: 1330578 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1184. Min Act: -0.0002

Data Index: 319693 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1194416 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1047391 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1067. Min Act: -0.0002

Data Index: 704975 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1150. Min Act: -0.0002

Data Index: 509253 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1089. Min Act: -0.0002

Data Index: 984062 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1037. Min Act: -0.0002

Data Index: 850463 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1003821 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1052. Min Act: -0.0002

Data Index: 218047 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1019. Min Act: -0.0002

Data Index: 624367 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1094. Min Act: -0.0002

Data Index: 417240 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1028. Min Act: -0.0002

Data Index: 638519 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1050. Min Act: -0.0002

Data Index: 315238 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0976. Min Act: -0.0002

Data Index: 23371 (C4 (Web Text))

Max Activating Token Index: 995