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

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

Neuron 5115 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: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0002

Data Index: 925793 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0759. Min Act: -0.0002

Data Index: 219270 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0814. Min Act: -0.0002

Data Index: 418882 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0751. Min Act: -0.0002

Data Index: 332131 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1620805 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0648. Min Act: -0.0002

Data Index: 593426 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1546619 (Python Code)

Max Activating Token Index: 547

Text #7

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0743. Min Act: -0.0002

Data Index: 283702 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0680. Min Act: -0.0002

Data Index: 996177 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1036910 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1591112 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1099172 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0712. Min Act: -0.0002

Data Index: 662137 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1268932 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1546411 (Python Code)

Max Activating Token Index: 585

Text #15

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0632. Min Act: -0.0002

Data Index: 925113 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1630252 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0656. Min Act: -0.0002

Data Index: 186320 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0680. Min Act: -0.0002

Data Index: 176848 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0702. Min Act: -0.0002

Data Index: 1124348 (C4 (Web Text))

Max Activating Token Index: 732