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

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

Neuron 978 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: 1.3825. Min Range: -1.3825

Max Act: 1.3825. Min Act: -0.0000

Data Index: 88623 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.3084. Min Act: -0.0000

Data Index: 1478629 (Python Code)

Max Activating Token Index: 174

Text #2

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1479010 (Python Code)

Max Activating Token Index: 68

Text #3

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.2734. Min Act: -0.0000

Data Index: 1634119 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1608134 (Python Code)

Max Activating Token Index: 469

Text #5

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1426522 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.2446. Min Act: -0.0000

Data Index: 438710 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1465220 (Python Code)

Max Activating Token Index: 629

Text #8

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1393268 (Python Code)

Max Activating Token Index: 525

Text #9

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1568256 (Python Code)

Max Activating Token Index: 632

Text #10

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1635602 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 1.3825. Min Range: -1.3825

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1445582 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 1.3825. Min Range: -1.3825

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1439099 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 1.3825. Min Range: -1.3825

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1386816 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 1.3825. Min Range: -1.3825

Max Act: 0.8602. Min Act: -0.0000

Data Index: 151504 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 1.3825. Min Range: -1.3825

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1359978 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 1.3825. Min Range: -1.3825

Max Act: 0.8852. Min Act: -0.0000

Data Index: 136014 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 1.3825. Min Range: -1.3825

Max Act: 0.8641. Min Act: -0.0000

Data Index: 809487 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.3825. Min Range: -1.3825

Max Act: 0.8373. Min Act: -0.0000

Data Index: 68986 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.3825. Min Range: -1.3825

Max Act: 0.8316. Min Act: -0.0000

Data Index: 770003 (C4 (Web Text))

Max Activating Token Index: 814