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

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

Neuron 5740 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: 0.3075. Min Range: -0.3075

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1545789 (Python Code)

Max Activating Token Index: 400

Text #1

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1470096 (Python Code)

Max Activating Token Index: 363

Text #2

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2611. Min Act: -0.0001

Data Index: 1523764 (Python Code)

Max Activating Token Index: 995

Text #3

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2799. Min Act: -0.0000

Data Index: 1422183 (Python Code)

Max Activating Token Index: 929

Text #4

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1453552 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2627. Min Act: -0.0001

Data Index: 1571776 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2651. Min Act: -0.0001

Data Index: 1563366 (Python Code)

Max Activating Token Index: 816

Text #7

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1592934 (Python Code)

Max Activating Token Index: 98

Text #8

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1410411 (Python Code)

Max Activating Token Index: 825

Text #9

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1463276 (Python Code)

Max Activating Token Index: 889

Text #10

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1577232 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1449889 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2591. Min Act: -0.0001

Data Index: 1361120 (Python Code)

Max Activating Token Index: 365

Text #13

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1459347 (Python Code)

Max Activating Token Index: 609

Text #14

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2474. Min Act: -0.0001

Data Index: 108005 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1490284 (Python Code)

Max Activating Token Index: 554

Text #16

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2561. Min Act: -0.0000

Data Index: 1628173 (Python Code)

Max Activating Token Index: 266

Text #17

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1569676 (Python Code)

Max Activating Token Index: 760

Text #18

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1468889 (Python Code)

Max Activating Token Index: 830

Text #19

Max Range: 0.3075. Min Range: -0.3075

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1560788 (Python Code)

Max Activating Token Index: 521