Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3278 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0115. Min Act: -0.0002

Data Index: 611447 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0106. Min Act: -0.0002

Data Index: 449583 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0092. Min Act: -0.0002

Data Index: 656315 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0094. Min Act: -0.0002

Data Index: 1429542 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0101. Min Act: -0.0002

Data Index: 539203 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0084. Min Act: -0.0002

Data Index: 1262443 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1355349 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0093. Min Act: -0.0002

Data Index: 277592 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0089. Min Act: -0.0002

Data Index: 108877 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0079. Min Act: -0.0002

Data Index: 615208 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0086. Min Act: -0.0002

Data Index: 890295 (C4 (Web Text))

Max Activating Token Index: 149

Text #11

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0095. Min Act: -0.0002

Data Index: 1199901 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0083. Min Act: -0.0002

Data Index: 939722 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0086. Min Act: -0.0002

Data Index: 987321 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0082. Min Act: -0.0002

Data Index: 299313 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0081. Min Act: -0.0002

Data Index: 903751 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0075. Min Act: -0.0002

Data Index: 148765 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0081. Min Act: -0.0002

Data Index: 1434705 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0078. Min Act: -0.0002

Data Index: 472341 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1055160 (C4 (Web Text))

Max Activating Token Index: 316