Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4280 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.2088. Min Act: -0.0000

Data Index: 974045 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1895. Min Act: -0.0000

Data Index: 702105 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1074153 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1910. Min Act: -0.0000

Data Index: 162476 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1826. Min Act: -0.0000

Data Index: 509073 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1126762 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1856. Min Act: -0.0000

Data Index: 440342 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1775. Min Act: -0.0000

Data Index: 1310434 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1629. Min Act: -0.0000

Data Index: 343807 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1568. Min Act: -0.0000

Data Index: 672687 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1048734 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1622. Min Act: -0.0000

Data Index: 311574 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1143870 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1644. Min Act: -0.0000

Data Index: 403222 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1616. Min Act: -0.0000

Data Index: 17687 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1509. Min Act: -0.0000

Data Index: 493997 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1605. Min Act: -0.0000

Data Index: 109782 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1632701 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1642. Min Act: -0.0000

Data Index: 150657 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.2088. Min Range: -0.2088

Max Act: 0.1546. Min Act: -0.0000

Data Index: 925364 (C4 (Web Text))

Max Activating Token Index: 114