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

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

Neuron 3001 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6720. Min Range: -2.6720

Max Act: 2.6720. Min Act: 0.0000

Data Index: 1461035 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 2.6720. Min Range: -2.6720

Max Act: 2.2297. Min Act: 0.0000

Data Index: 1371387 (Python Code)

Max Activating Token Index: 378

Text #2

Max Range: 2.6720. Min Range: -2.6720

Max Act: 2.1207. Min Act: -0.0000

Data Index: 1470580 (Python Code)

Max Activating Token Index: 634

Text #3

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.9596. Min Act: 0.0002

Data Index: 1420892 (Python Code)

Max Activating Token Index: 660

Text #4

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.8951. Min Act: -0.0000

Data Index: 1410415 (Python Code)

Max Activating Token Index: 735

Text #5

Max Range: 2.6720. Min Range: -2.6720

Max Act: 2.0503. Min Act: -0.0000

Data Index: 1644593 (Python Code)

Max Activating Token Index: 352

Text #6

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.9722. Min Act: 0.0000

Data Index: 1362606 (Python Code)

Max Activating Token Index: 665

Text #7

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.9423. Min Act: -0.0000

Data Index: 1476146 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.8357. Min Act: 0.0001

Data Index: 1386382 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.7757. Min Act: -0.0000

Data Index: 1410173 (Python Code)

Max Activating Token Index: 258

Text #10

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.6716. Min Act: -0.0000

Data Index: 1616709 (Python Code)

Max Activating Token Index: 823

Text #11

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.7357. Min Act: 0.0000

Data Index: 1613997 (Python Code)

Max Activating Token Index: 835

Text #12

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.7452. Min Act: -0.0000

Data Index: 302600 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.7285. Min Act: -0.0000

Data Index: 858248 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.6836. Min Act: -0.0000

Data Index: 1485931 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.6839. Min Act: -0.0000

Data Index: 1475897 (Python Code)

Max Activating Token Index: 566

Text #16

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.5881. Min Act: -0.0000

Data Index: 1465572 (Python Code)

Max Activating Token Index: 228

Text #17

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1653692 (Python Code)

Max Activating Token Index: 418

Text #18

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.6526. Min Act: 0.0001

Data Index: 1477538 (Python Code)

Max Activating Token Index: 447

Text #19

Max Range: 2.6720. Min Range: -2.6720

Max Act: 1.5417. Min Act: -0.0000

Data Index: 1390661 (Python Code)

Max Activating Token Index: 498