Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1618 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1020. Min Act: -0.0002

Data Index: 1040557 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1548851 (Python Code)

Max Activating Token Index: 354

Text #2

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1627722 (Python Code)

Max Activating Token Index: 315

Text #3

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0942. Min Act: -0.0002

Data Index: 517122 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1530980 (Python Code)

Max Activating Token Index: 116

Text #5

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1600477 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1436247 (Python Code)

Max Activating Token Index: 216

Text #7

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1634908 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1429197 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1456963 (Python Code)

Max Activating Token Index: 282

Text #10

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1467708 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0882. Min Act: -0.0002

Data Index: 417342 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0922. Min Act: -0.0002

Data Index: 143547 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0891. Min Act: -0.0002

Data Index: 403045 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0855. Min Act: -0.0002

Data Index: 40505 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1587225 (Python Code)

Max Activating Token Index: 232

Text #16

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1641000 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1546541 (Python Code)

Max Activating Token Index: 249

Text #18

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1409442 (Python Code)

Max Activating Token Index: 524

Text #19

Max Range: 0.1049. Min Range: -0.1049

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1540464 (Python Code)

Max Activating Token Index: 146