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

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

Neuron 360 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1654219 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0079. Min Act: -0.0003

Data Index: 856668 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0003

Data Index: 794430 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1508092 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0003

Data Index: 1466865 (Python Code)

Max Activating Token Index: 220

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0078. Min Act: -0.0003

Data Index: 181557 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0003

Data Index: 473529 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1513085 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1317670 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1565575 (Python Code)

Max Activating Token Index: 932

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1215015 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1526195 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0004

Data Index: 206926 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0077. Min Act: -0.0004

Data Index: 1248159 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0003

Data Index: 791842 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0003

Data Index: 412368 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1159209 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1636069 (Python Code)

Max Activating Token Index: 665

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1387364 (Python Code)

Max Activating Token Index: 38

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1226135 (C4 (Web Text))

Max Activating Token Index: 124