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

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

Neuron 4589 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: 8.2275. Min Range: -8.2275

Max Act: 8.2017. Min Act: -0.0000

Data Index: 1384410 (Python Code)

Max Activating Token Index: 754

Text #1

Max Range: 8.2275. Min Range: -8.2275

Max Act: 8.2275. Min Act: -0.0000

Data Index: 1586326 (Python Code)

Max Activating Token Index: 725

Text #2

Max Range: 8.2275. Min Range: -8.2275

Max Act: 8.0438. Min Act: -0.0000

Data Index: 1505990 (Python Code)

Max Activating Token Index: 848

Text #3

Max Range: 8.2275. Min Range: -8.2275

Max Act: 8.0335. Min Act: -0.0000

Data Index: 1650484 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 8.2275. Min Range: -8.2275

Max Act: 8.1734. Min Act: -0.0000

Data Index: 1441868 (Python Code)

Max Activating Token Index: 800

Text #5

Max Range: 8.2275. Min Range: -8.2275

Max Act: 8.0793. Min Act: -0.0000

Data Index: 1624735 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 8.2275. Min Range: -8.2275

Max Act: 7.8902. Min Act: -0.0000

Data Index: 1419368 (Python Code)

Max Activating Token Index: 766

Text #7

Max Range: 8.2275. Min Range: -8.2275

Max Act: 7.7525. Min Act: -0.0000

Data Index: 1648465 (Python Code)

Max Activating Token Index: 549

Text #8

Max Range: 8.2275. Min Range: -8.2275

Max Act: 7.7328. Min Act: -0.0000

Data Index: 1489226 (Python Code)

Max Activating Token Index: 647

Text #9

Max Range: 8.2275. Min Range: -8.2275

Max Act: 7.8444. Min Act: -0.0000

Data Index: 1418256 (Python Code)

Max Activating Token Index: 900

Text #10

Max Range: 8.2275. Min Range: -8.2275

Max Act: 7.7029. Min Act: -0.0000

Data Index: 1598184 (Python Code)

Max Activating Token Index: 191

Text #11

Max Range: 8.2275. Min Range: -8.2275

Max Act: 7.1644. Min Act: -0.0000

Data Index: 1399938 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 8.2275. Min Range: -8.2275

Max Act: 6.7866. Min Act: -0.0000

Data Index: 1456752 (Python Code)

Max Activating Token Index: 690

Text #13

Max Range: 8.2275. Min Range: -8.2275

Max Act: 6.5471. Min Act: -0.0000

Data Index: 1592466 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 8.2275. Min Range: -8.2275

Max Act: 6.8367. Min Act: -0.0000

Data Index: 1546891 (Python Code)

Max Activating Token Index: 942

Text #15

Max Range: 8.2275. Min Range: -8.2275

Max Act: 6.5185. Min Act: -0.0000

Data Index: 1525149 (Python Code)

Max Activating Token Index: 971

Text #16

Max Range: 8.2275. Min Range: -8.2275

Max Act: 6.0717. Min Act: -0.0000

Data Index: 1497856 (Python Code)

Max Activating Token Index: 418

Text #17

Max Range: 8.2275. Min Range: -8.2275

Max Act: 6.0746. Min Act: -0.0000

Data Index: 1508280 (Python Code)

Max Activating Token Index: 294

Text #18

Max Range: 8.2275. Min Range: -8.2275

Max Act: 6.0695. Min Act: -0.0000

Data Index: 1626702 (Python Code)

Max Activating Token Index: 1005

Text #19

Max Range: 8.2275. Min Range: -8.2275

Max Act: 5.9414. Min Act: -0.0000

Data Index: 1386934 (Python Code)

Max Activating Token Index: 940