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

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

Neuron 375 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: 0.2412. Min Range: -0.2412

Max Act: 0.2412. Min Act: -0.0000

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2399. Min Act: -0.0000

Data Index: 325546 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2143. Min Act: -0.0000

Data Index: 739915 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1990. Min Act: -0.0000

Data Index: 907432 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1061861 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1932. Min Act: -0.0000

Data Index: 951774 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1864. Min Act: -0.0000

Data Index: 439316 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1682. Min Act: -0.0000

Data Index: 1569038 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1315953 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1407702 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1404102 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1691. Min Act: -0.0000

Data Index: 149244 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1655544 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1809. Min Act: -0.0000

Data Index: 613481 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1392897 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1621. Min Act: -0.0000

Data Index: 162428 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1853. Min Act: -0.0000

Data Index: 883490 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1647939 (Python Code)

Max Activating Token Index: 1007

Text #18

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1632. Min Act: -0.0000

Data Index: 1557062 (Python Code)

Max Activating Token Index: 900

Text #19

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1111883 (C4 (Web Text))

Max Activating Token Index: 101