Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2599 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1199. Min Act: -0.0002

Data Index: 1012655 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1102. Min Act: -0.0002

Data Index: 61262 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1067. Min Act: -0.0002

Data Index: 457701 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1132. Min Act: -0.0002

Data Index: 688647 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1121. Min Act: -0.0002

Data Index: 436330 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1087. Min Act: -0.0002

Data Index: 483491 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1130. Min Act: -0.0002

Data Index: 182689 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1350155 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1058 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1097. Min Act: -0.0002

Data Index: 912797 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1022. Min Act: -0.0002

Data Index: 62750 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1057. Min Act: -0.0002

Data Index: 377047 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1319694 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1013709 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1071. Min Act: -0.0002

Data Index: 1103945 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1058. Min Act: -0.0002

Data Index: 260481 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0956. Min Act: -0.0002

Data Index: 636558 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1347724 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.1018. Min Act: -0.0002

Data Index: 72168 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.1199. Min Range: -0.1199

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1275832 (C4 (Web Text))

Max Activating Token Index: 849