Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2592 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0003

Data Index: 24803 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1158. Min Act: -0.0003

Data Index: 102072 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1073. Min Act: -0.0003

Data Index: 800542 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1143. Min Act: -0.0003

Data Index: 642394 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1084. Min Act: -0.0003

Data Index: 167758 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1076. Min Act: -0.0003

Data Index: 1134693 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1037. Min Act: -0.0003

Data Index: 949134 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1044. Min Act: -0.0003

Data Index: 524500 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1067. Min Act: -0.0003

Data Index: 370306 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1076. Min Act: -0.0003

Data Index: 409948 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1054. Min Act: -0.0003

Data Index: 1179836 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1068. Min Act: -0.0003

Data Index: 1068782 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1051. Min Act: -0.0003

Data Index: 333011 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1023. Min Act: -0.0003

Data Index: 114542 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1049. Min Act: -0.0003

Data Index: 749268 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0997. Min Act: -0.0003

Data Index: 1019688 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1024. Min Act: -0.0003

Data Index: 272995 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0991. Min Act: -0.0003

Data Index: 1105603 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1038. Min Act: -0.0003

Data Index: 449771 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1019. Min Act: -0.0003

Data Index: 877592 (C4 (Web Text))

Max Activating Token Index: 987