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

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

Neuron 3770 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0002

Data Index: 1551174 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1619770 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1391579 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1526283 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1633413 (Python Code)

Max Activating Token Index: 74

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1363103 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0077. Min Act: -0.0002

Data Index: 504446 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0078. Min Act: -0.0002

Data Index: 1593266 (Python Code)

Max Activating Token Index: 110

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1267659 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1478202 (Python Code)

Max Activating Token Index: 168

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1612607 (Python Code)

Max Activating Token Index: 230

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0075. Min Act: -0.0002

Data Index: 299300 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1547124 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0075. Min Act: -0.0002

Data Index: 811186 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0074. Min Act: -0.0002

Data Index: 1567337 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0073. Min Act: -0.0002

Data Index: 840482 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0072. Min Act: -0.0002

Data Index: 568898 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1162807 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0070. Min Act: -0.0002

Data Index: 257448 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1418892 (Python Code)

Max Activating Token Index: 331