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

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

Neuron 5696 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: 0.2042. Min Range: -0.2042

Max Act: 0.1890. Min Act: -0.0000

Data Index: 773021 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1156050 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.2013. Min Act: -0.0000

Data Index: 675369 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1729. Min Act: -0.0000

Data Index: 302533 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1811. Min Act: -0.0000

Data Index: 180821 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1743. Min Act: -0.0000

Data Index: 925152 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1749. Min Act: -0.0000

Data Index: 1302013 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1031339 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1791. Min Act: -0.0000

Data Index: 726829 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1745. Min Act: -0.0000

Data Index: 242333 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1701. Min Act: -0.0000

Data Index: 214753 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1617. Min Act: -0.0000

Data Index: 963330 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1484679 (Python Code)

Max Activating Token Index: 876

Text #13

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1643. Min Act: -0.0000

Data Index: 751206 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1340683 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1591772 (Python Code)

Max Activating Token Index: 333

Text #16

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1563250 (Python Code)

Max Activating Token Index: 706

Text #17

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1465282 (Python Code)

Max Activating Token Index: 821

Text #18

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1299835 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.2042. Min Range: -0.2042

Max Act: 0.1501. Min Act: -0.0000

Data Index: 925974 (C4 (Web Text))

Max Activating Token Index: 290