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

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

Neuron 5179 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9804. Min Act: -0.0000

Data Index: 566769 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9498. Min Act: -0.0000

Data Index: 250386 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1550589 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1355514 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9307. Min Act: -0.0000

Data Index: 301532 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9258. Min Act: -0.0000

Data Index: 956882 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9241. Min Act: -0.0000

Data Index: 274802 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9169. Min Act: -0.0000

Data Index: 924379 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9328. Min Act: -0.0000

Data Index: 368723 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1512680 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8824. Min Act: -0.0000

Data Index: 1321445 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8560. Min Act: -0.0000

Data Index: 43302 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.9063. Min Act: -0.0000

Data Index: 881922 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8612. Min Act: -0.0000

Data Index: 242618 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8614. Min Act: -0.0000

Data Index: 804442 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1435506 (Python Code)

Max Activating Token Index: 571

Text #16

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8877. Min Act: -0.0000

Data Index: 591798 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8782. Min Act: -0.0000

Data Index: 1086491 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8293. Min Act: -0.0000

Data Index: 260050 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.9804. Min Range: -0.9804

Max Act: 0.8596. Min Act: -0.0000

Data Index: 350454 (C4 (Web Text))

Max Activating Token Index: 877