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

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

Neuron 725 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1546529 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1380584 (Python Code)

Max Activating Token Index: 242

Text #2

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1226679 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1100890 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2739. Min Act: -0.0000

Data Index: 781462 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1554427 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1556698 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1616120 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1334937 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1595967 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1630211 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.1907. Min Act: -0.0000

Data Index: 782819 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2425. Min Act: -0.0000

Data Index: 543592 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1520740 (Python Code)

Max Activating Token Index: 459

Text #14

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.1511. Min Act: -0.0000

Data Index: 162500 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.1512. Min Act: -0.0000

Data Index: 1527715 (Python Code)

Max Activating Token Index: 738

Text #16

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1541129 (Python Code)

Max Activating Token Index: 692

Text #17

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1249329 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.1769. Min Act: -0.0000

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.1634. Min Act: -0.0000

Data Index: 805280 (C4 (Web Text))

Max Activating Token Index: 905