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

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

Neuron 4950 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1509232 (Python Code)

Max Activating Token Index: 387

Text #1

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1572569 (Python Code)

Max Activating Token Index: 961

Text #2

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.7813. Min Act: -0.0000

Data Index: 1487831 (Python Code)

Max Activating Token Index: 98

Text #3

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1602290 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1528456 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1372771 (Python Code)

Max Activating Token Index: 789

Text #6

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1640281 (Python Code)

Max Activating Token Index: 656

Text #7

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6434. Min Act: -0.0000

Data Index: 1597342 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1413553 (Python Code)

Max Activating Token Index: 652

Text #9

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1615919 (Python Code)

Max Activating Token Index: 778

Text #10

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1570925 (Python Code)

Max Activating Token Index: 156

Text #11

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1652836 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1580377 (Python Code)

Max Activating Token Index: 708

Text #13

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1496462 (Python Code)

Max Activating Token Index: 367

Text #14

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1625624 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1613928 (Python Code)

Max Activating Token Index: 805

Text #16

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1483321 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1499761 (Python Code)

Max Activating Token Index: 372

Text #18

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.6340. Min Act: -0.0000

Data Index: 1438623 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 0.8479. Min Range: -0.8479

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1542607 (Python Code)

Max Activating Token Index: 280