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

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

Neuron 2906 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: 0.0852. Min Range: -0.0852

Max Act: 0.0852. Min Act: -0.0000

Data Index: 586139 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1007519 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1147684 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0761. Min Act: -0.0000

Data Index: 75790 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1221923 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1006464 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0716. Min Act: -0.0000

Data Index: 817633 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1647304 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0706. Min Act: -0.0000

Data Index: 30297 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0648. Min Act: -0.0000

Data Index: 474921 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0714. Min Act: -0.0000

Data Index: 202848 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1250938 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0638. Min Act: -0.0000

Data Index: 560036 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0630. Min Act: -0.0000

Data Index: 717385 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0646. Min Act: -0.0000

Data Index: 1267857 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1411716 (Python Code)

Max Activating Token Index: 691

Text #16

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0638. Min Act: -0.0000

Data Index: 757421 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1225083 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0612. Min Act: -0.0000

Data Index: 697014 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 0.0852. Min Range: -0.0852

Max Act: 0.0581. Min Act: -0.0000

Data Index: 486621 (C4 (Web Text))

Max Activating Token Index: 696