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

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

Neuron 5990 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: 0.2252. Min Range: -0.2252

Max Act: 0.2044. Min Act: -0.0000

Data Index: 871092 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1056156 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1067380 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1960. Min Act: -0.0000

Data Index: 327922 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1883. Min Act: -0.0000

Data Index: 971139 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1361372 (Python Code)

Max Activating Token Index: 732

Text #6

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1963. Min Act: -0.0000

Data Index: 1228218 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1955. Min Act: -0.0000

Data Index: 841481 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1835. Min Act: -0.0000

Data Index: 347361 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1950. Min Act: -0.0000

Data Index: 1271133 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1801. Min Act: -0.0000

Data Index: 298331 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1146206 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1363372 (Python Code)

Max Activating Token Index: 333

Text #13

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1767. Min Act: -0.0000

Data Index: 160298 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1598. Min Act: -0.0000

Data Index: 223826 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1640. Min Act: -0.0000

Data Index: 561493 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1644. Min Act: -0.0000

Data Index: 407397 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1590. Min Act: -0.0000

Data Index: 101437 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1686. Min Act: -0.0000

Data Index: 990515 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.2252. Min Range: -0.2252

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1018198 (C4 (Web Text))

Max Activating Token Index: 536