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

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

Neuron 1412 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: 0.1144. Min Range: -0.1144

Max Act: 0.1140. Min Act: -0.0005

Data Index: 135640 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1051. Min Act: -0.0005

Data Index: 1046387 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1105. Min Act: -0.0005

Data Index: 442712 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1130. Min Act: -0.0005

Data Index: 456560 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1089. Min Act: -0.0005

Data Index: 228355 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1106. Min Act: -0.0005

Data Index: 862505 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1124. Min Act: -0.0005

Data Index: 279591 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0005

Data Index: 1268337 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1105. Min Act: -0.0005

Data Index: 301721 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1055. Min Act: -0.0005

Data Index: 908002 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1070. Min Act: -0.0005

Data Index: 1261061 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1081. Min Act: -0.0005

Data Index: 1284574 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1036. Min Act: -0.0005

Data Index: 648344 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1053. Min Act: -0.0005

Data Index: 83280 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0981. Min Act: -0.0005

Data Index: 408640 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1038. Min Act: -0.0005

Data Index: 989351 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0952. Min Act: -0.0005

Data Index: 1349504 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1050. Min Act: -0.0005

Data Index: 1279648 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1083. Min Act: -0.0005

Data Index: 49184 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1057. Min Act: -0.0005

Data Index: 101655 (C4 (Web Text))

Max Activating Token Index: 798