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

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

Neuron 3281 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1640060 (Python Code)

Max Activating Token Index: 1007

Text #1

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1425097 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1583024 (Python Code)

Max Activating Token Index: 704

Text #3

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1605561 (Python Code)

Max Activating Token Index: 677

Text #4

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1637944 (Python Code)

Max Activating Token Index: 626

Text #5

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1598521 (Python Code)

Max Activating Token Index: 638

Text #6

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1525562 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1614054 (Python Code)

Max Activating Token Index: 838

Text #8

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1606105 (Python Code)

Max Activating Token Index: 682

Text #9

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1491387 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2758. Min Act: -0.0000

Data Index: 1467186 (Python Code)

Max Activating Token Index: 577

Text #11

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1521011 (Python Code)

Max Activating Token Index: 520

Text #12

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1518356 (Python Code)

Max Activating Token Index: 541

Text #13

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1361231 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1610355 (Python Code)

Max Activating Token Index: 572

Text #15

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1631934 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1613680 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1591360 (Python Code)

Max Activating Token Index: 433

Text #18

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2729. Min Act: -0.0000

Data Index: 1589720 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 0.3329. Min Range: -0.3329

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1607984 (Python Code)

Max Activating Token Index: 363