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

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

Neuron 5185 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1628406 (Python Code)

Max Activating Token Index: 359

Text #1

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1604210 (Python Code)

Max Activating Token Index: 809

Text #2

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1159. Min Act: -0.0000

Data Index: 1484627 (Python Code)

Max Activating Token Index: 690

Text #3

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1682. Min Act: -0.0000

Data Index: 1460721 (Python Code)

Max Activating Token Index: 837

Text #4

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1375223 (Python Code)

Max Activating Token Index: 528

Text #5

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1546408 (Python Code)

Max Activating Token Index: 242

Text #6

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1415110 (Python Code)

Max Activating Token Index: 449

Text #7

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1496178 (Python Code)

Max Activating Token Index: 913

Text #8

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1418205 (Python Code)

Max Activating Token Index: 844

Text #9

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1639948 (Python Code)

Max Activating Token Index: 388

Text #10

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.2194. Min Act: -0.0000

Data Index: 1626802 (Python Code)

Max Activating Token Index: 414

Text #11

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1484922 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1374. Min Act: -0.0000

Data Index: 1485386 (Python Code)

Max Activating Token Index: 725

Text #13

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1634387 (Python Code)

Max Activating Token Index: 593

Text #14

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.1136. Min Act: -0.0000

Data Index: 1409120 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0917. Min Act: -0.0000

Data Index: 1606739 (Python Code)

Max Activating Token Index: 801

Text #16

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0475. Min Act: -0.0000

Data Index: 1533998 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1595043 (Python Code)

Max Activating Token Index: 557

Text #18

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1419000 (Python Code)

Max Activating Token Index: 403

Text #19

Max Range: 1.3759. Min Range: -1.3759

Max Act: 1.0068. Min Act: -0.0000

Data Index: 1406470 (Python Code)

Max Activating Token Index: 258