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

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

Neuron 2259 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.5832. Min Act: -0.0000

Data Index: 444680 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.4838. Min Act: -0.0000

Data Index: 179311 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.3765. Min Act: -0.0000

Data Index: 1010783 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.4046. Min Act: -0.0000

Data Index: 1406722 (Python Code)

Max Activating Token Index: 681

Text #4

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.3099. Min Act: -0.0000

Data Index: 1407855 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1403409 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.2968. Min Act: -0.0000

Data Index: 1547875 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1846. Min Act: -0.0000

Data Index: 1616790 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1508. Min Act: -0.0000

Data Index: 320021 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.1488. Min Act: -0.0000

Data Index: 1256118 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.0556. Min Act: -0.0000

Data Index: 1605952 (Python Code)

Max Activating Token Index: 770

Text #11

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1085065 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.0393. Min Act: -0.0000

Data Index: 377665 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1035910 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1556798 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.0826. Min Act: -0.0000

Data Index: 87911 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 1.5832. Min Range: -1.5832

Max Act: 0.9703. Min Act: -0.0000

Data Index: 632597 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 1.5832. Min Range: -1.5832

Max Act: 0.9967. Min Act: -0.0000

Data Index: 508918 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1511182 (Python Code)

Max Activating Token Index: 227

Text #19

Max Range: 1.5832. Min Range: -1.5832

Max Act: 1.0800. Min Act: -0.0000

Data Index: 617481 (C4 (Web Text))

Max Activating Token Index: 42