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

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

Neuron 4848 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2691. Min Act: -0.0000

Data Index: 98478 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1968. Min Act: -0.0000

Data Index: 222926 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1035597 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.2068. Min Act: -0.0000

Data Index: 423270 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1980. Min Act: -0.0000

Data Index: 645182 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1789. Min Act: -0.0000

Data Index: 610315 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1867. Min Act: -0.0000

Data Index: 106006 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1623024 (Python Code)

Max Activating Token Index: 953

Text #8

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1307879 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1829. Min Act: -0.0000

Data Index: 176796 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1797. Min Act: -0.0000

Data Index: 778642 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1007591 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1736. Min Act: -0.0000

Data Index: 655498 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1607. Min Act: -0.0000

Data Index: 333272 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1162788 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1629. Min Act: -0.0000

Data Index: 438657 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1730. Min Act: -0.0000

Data Index: 635124 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1605057 (Python Code)

Max Activating Token Index: 951

Text #18

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1680. Min Act: -0.0000

Data Index: 841565 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.2691. Min Range: -0.2691

Max Act: 0.1650. Min Act: -0.0000

Data Index: 847986 (C4 (Web Text))

Max Activating Token Index: 431