Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 929 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.8653. Min Act: -0.0001

Data Index: 12315 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.8679. Min Act: -0.0001

Data Index: 1563121 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.3598. Min Act: -0.0001

Data Index: 916938 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.3582. Min Act: -0.0001

Data Index: 1428364 (Python Code)

Max Activating Token Index: 15

Text #4

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.3834. Min Act: -0.0001

Data Index: 374883 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.2162. Min Act: -0.0001

Data Index: 243765 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.2442. Min Act: -0.0001

Data Index: 1593607 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.2544. Min Act: -0.0001

Data Index: 795912 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.2401. Min Act: -0.0001

Data Index: 327209 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.2404. Min Act: -0.0001

Data Index: 1603756 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.1524. Min Act: -0.0001

Data Index: 763143 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.1709. Min Act: -0.0001

Data Index: 1369771 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.0959. Min Act: -0.0001

Data Index: 1404723 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.2131. Min Act: -0.0001

Data Index: 1555918 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.1027. Min Act: -0.0001

Data Index: 1596594 (Python Code)

Max Activating Token Index: 10

Text #15

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.0914. Min Act: -0.0001

Data Index: 679653 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.1650. Min Act: -0.0001

Data Index: 1157673 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.1897. Min Act: -0.0001

Data Index: 53762 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.1185. Min Act: -0.0001

Data Index: 449849 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 1.8679. Min Range: -1.8679

Max Act: 1.1130. Min Act: -0.0001

Data Index: 698574 (C4 (Web Text))

Max Activating Token Index: 840