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

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

Neuron 1178 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: 0.1533. Min Range: -0.1533

Max Act: 0.1533. Min Act: -0.0005

Data Index: 92030 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1248. Min Act: -0.0005

Data Index: 890302 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1250. Min Act: -0.0005

Data Index: 772891 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1257. Min Act: -0.0005

Data Index: 675149 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1193. Min Act: -0.0005

Data Index: 1182737 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1200. Min Act: -0.0005

Data Index: 1303819 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1144. Min Act: -0.0005

Data Index: 210773 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1224. Min Act: -0.0005

Data Index: 207576 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1111. Min Act: -0.0005

Data Index: 830451 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1096. Min Act: -0.0005

Data Index: 36042 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1114. Min Act: -0.0005

Data Index: 1275146 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1058. Min Act: -0.0005

Data Index: 221047 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1039. Min Act: -0.0005

Data Index: 1096026 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1076. Min Act: -0.0005

Data Index: 928890 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1031. Min Act: -0.0005

Data Index: 531590 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1027. Min Act: -0.0005

Data Index: 566837 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1045. Min Act: -0.0005

Data Index: 986718 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1029. Min Act: -0.0005

Data Index: 1197199 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1017. Min Act: -0.0005

Data Index: 551936 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.1533. Min Range: -0.1533

Max Act: 0.1042. Min Act: -0.0005

Data Index: 582576 (C4 (Web Text))

Max Activating Token Index: 774