Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 677 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0093. Min Act: -0.0005

Data Index: 980023 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0089. Min Act: -0.0005

Data Index: 810187 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0084. Min Act: -0.0005

Data Index: 1128026 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0080. Min Act: -0.0006

Data Index: 601846 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0081. Min Act: -0.0005

Data Index: 697549 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0078. Min Act: -0.0006

Data Index: 695952 (C4 (Web Text))

Max Activating Token Index: 687

Text #6

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1162691 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1185222 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1190414 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0075. Min Act: -0.0006

Data Index: 388610 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0075. Min Act: -0.0006

Data Index: 126580 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0073. Min Act: -0.0006

Data Index: 494786 (C4 (Web Text))

Max Activating Token Index: 821

Text #12

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0006

Data Index: 374063 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0074. Min Act: -0.0006

Data Index: 694203 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0072. Min Act: -0.0006

Data Index: 21539 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0072. Min Act: -0.0006

Data Index: 660306 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1165596 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1407424 (Python Code)

Max Activating Token Index: 877

Text #18

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0071. Min Act: -0.0006

Data Index: 153381 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0093. Min Range: -0.0093

Max Act: 0.0071. Min Act: -0.0006

Data Index: 218078 (C4 (Web Text))

Max Activating Token Index: 44