Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3683 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.8083. Min Act: -0.0002

Data Index: 934679 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6183. Min Act: -0.0001

Data Index: 539187 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6167. Min Act: -0.0002

Data Index: 69060 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5590. Min Act: -0.0001

Data Index: 965154 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.6056. Min Act: -0.0002

Data Index: 222593 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5748. Min Act: -0.0001

Data Index: 975721 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5542. Min Act: -0.0002

Data Index: 613804 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5330. Min Act: -0.0002

Data Index: 818823 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5274. Min Act: -0.0002

Data Index: 1080187 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5511. Min Act: -0.0002

Data Index: 1156555 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.4891. Min Act: -0.0001

Data Index: 879013 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.4992. Min Act: -0.0002

Data Index: 186053 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5331. Min Act: -0.0001

Data Index: 1288263 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.4971. Min Act: -0.0002

Data Index: 52982 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5119. Min Act: -0.0002

Data Index: 100860 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.4739. Min Act: -0.0002

Data Index: 1004068 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.4885. Min Act: -0.0001

Data Index: 115735 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.4945. Min Act: -0.0002

Data Index: 177239 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.4824. Min Act: -0.0002

Data Index: 1076771 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.8083. Min Range: -0.8083

Max Act: 0.5087. Min Act: -0.0002

Data Index: 894185 (C4 (Web Text))

Max Activating Token Index: 247