Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2199 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1534912 (Python Code)

Max Activating Token Index: 197

Text #1

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1536997 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1223222 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1550884 (Python Code)

Max Activating Token Index: 756

Text #4

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1911. Min Act: -0.0000

Data Index: 355902 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1798. Min Act: -0.0000

Data Index: 548884 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1843. Min Act: -0.0000

Data Index: 973958 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1515754 (Python Code)

Max Activating Token Index: 878

Text #8

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1561. Min Act: -0.0000

Data Index: 579236 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1672. Min Act: -0.0000

Data Index: 708904 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1697. Min Act: -0.0000

Data Index: 808656 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1657. Min Act: -0.0000

Data Index: 973919 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1783. Min Act: -0.0000

Data Index: 759873 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1685. Min Act: -0.0000

Data Index: 395920 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1647. Min Act: -0.0000

Data Index: 248225 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1695. Min Act: -0.0000

Data Index: 318333 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1832. Min Act: -0.0000

Data Index: 323576 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1848. Min Act: -0.0000

Data Index: 533927 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1849. Min Act: -0.0000

Data Index: 976321 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.2602. Min Range: -0.2602

Max Act: 0.1663. Min Act: -0.0000

Data Index: 743862 (C4 (Web Text))

Max Activating Token Index: 120