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

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

Neuron 2050 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1851. Min Act: -0.0001

Data Index: 678233 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1595. Min Act: -0.0001

Data Index: 69093 (C4 (Web Text))

Max Activating Token Index: 226

Text #2

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1727. Min Act: -0.0001

Data Index: 142992 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1845. Min Act: -0.0001

Data Index: 543116 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1794. Min Act: -0.0000

Data Index: 463828 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1669. Min Act: -0.0001

Data Index: 986023 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1992. Min Act: -0.0001

Data Index: 124587 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1638. Min Act: -0.0001

Data Index: 994463 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1615. Min Act: -0.0000

Data Index: 20286 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1437. Min Act: -0.0001

Data Index: 334231 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1513. Min Act: -0.0001

Data Index: 845520 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1087698 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1391. Min Act: -0.0001

Data Index: 271293 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1519. Min Act: -0.0001

Data Index: 554400 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1501. Min Act: -0.0001

Data Index: 545144 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1288495 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1240521 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1494. Min Act: -0.0001

Data Index: 1340641 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1477. Min Act: -0.0001

Data Index: 419817 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.1992. Min Range: -0.1992

Max Act: 0.1430. Min Act: -0.0001

Data Index: 31722 (C4 (Web Text))

Max Activating Token Index: 6