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

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

Neuron 3996 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1626814 (Python Code)

Max Activating Token Index: 231

Text #1

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1513719 (Python Code)

Max Activating Token Index: 493

Text #2

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1642650 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1550996 (Python Code)

Max Activating Token Index: 512

Text #4

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1571386 (Python Code)

Max Activating Token Index: 581

Text #5

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1615834 (Python Code)

Max Activating Token Index: 607

Text #6

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1596906 (Python Code)

Max Activating Token Index: 985

Text #7

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1477017 (Python Code)

Max Activating Token Index: 393

Text #8

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1369123 (Python Code)

Max Activating Token Index: 421

Text #9

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1471529 (Python Code)

Max Activating Token Index: 540

Text #10

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1627477 (Python Code)

Max Activating Token Index: 354

Text #11

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1443454 (Python Code)

Max Activating Token Index: 516

Text #12

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6718. Min Act: -0.0000

Data Index: 357808 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1597805 (Python Code)

Max Activating Token Index: 557

Text #14

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1569288 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1651969 (Python Code)

Max Activating Token Index: 859

Text #16

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1384336 (Python Code)

Max Activating Token Index: 342

Text #17

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1656843 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1432035 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1651056 (Python Code)

Max Activating Token Index: 833