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

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

Neuron 1321 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2508. Min Act: -0.0002

Data Index: 103221 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2294. Min Act: -0.0002

Data Index: 460632 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2148. Min Act: -0.0002

Data Index: 319501 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2245. Min Act: -0.0002

Data Index: 725801 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2116. Min Act: -0.0002

Data Index: 535073 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2135. Min Act: -0.0002

Data Index: 1333912 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1986. Min Act: -0.0002

Data Index: 412372 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1984. Min Act: -0.0002

Data Index: 812716 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1909. Min Act: -0.0002

Data Index: 247527 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1760. Min Act: -0.0002

Data Index: 9291 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1740. Min Act: -0.0002

Data Index: 1124576 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1636. Min Act: -0.0002

Data Index: 211383 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1609. Min Act: -0.0002

Data Index: 206772 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1657. Min Act: -0.0002

Data Index: 510357 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1643. Min Act: -0.0002

Data Index: 390304 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1578. Min Act: -0.0002

Data Index: 470550 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1499. Min Act: -0.0002

Data Index: 42661 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1472. Min Act: -0.0002

Data Index: 780912 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1450. Min Act: -0.0002

Data Index: 190203 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1461. Min Act: -0.0002

Data Index: 510659 (C4 (Web Text))

Max Activating Token Index: 449