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

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

Neuron 259 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0110. Min Act: -0.0003

Data Index: 239586 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1582293 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0092. Min Act: -0.0003

Data Index: 125428 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0099. Min Act: -0.0003

Data Index: 960506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1446874 (Python Code)

Max Activating Token Index: 477

Text #5

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0101. Min Act: -0.0004

Data Index: 906444 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0100. Min Act: -0.0003

Data Index: 1425120 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1050751 (C4 (Web Text))

Max Activating Token Index: 12

Text #8

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1538314 (Python Code)

Max Activating Token Index: 200

Text #9

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0091. Min Act: -0.0003

Data Index: 91742 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0093. Min Act: -0.0004

Data Index: 10095 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0093. Min Act: -0.0003

Data Index: 590742 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0087. Min Act: -0.0004

Data Index: 1030744 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0091. Min Act: -0.0004

Data Index: 1066347 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1365764 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0084. Min Act: -0.0003

Data Index: 233129 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0071. Min Act: -0.0004

Data Index: 1267340 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0074. Min Act: -0.0003

Data Index: 163886 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0097. Min Act: -0.0004

Data Index: 1342148 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 0.0115. Min Range: -0.0115

Max Act: 0.0073. Min Act: -0.0003

Data Index: 866175 (C4 (Web Text))

Max Activating Token Index: 674