Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 9 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1373110 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1377844 (Python Code)

Max Activating Token Index: 677

Text #2

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1638744 (Python Code)

Max Activating Token Index: 935

Text #3

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1566122 (Python Code)

Max Activating Token Index: 753

Text #4

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1559065 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1515983 (Python Code)

Max Activating Token Index: 447

Text #6

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1512117 (Python Code)

Max Activating Token Index: 290

Text #7

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1438931 (Python Code)

Max Activating Token Index: 320

Text #8

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1437578 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1642348 (Python Code)

Max Activating Token Index: 823

Text #10

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1566. Min Act: -0.0000

Data Index: 1580417 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1624490 (Python Code)

Max Activating Token Index: 976

Text #12

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1589795 (Python Code)

Max Activating Token Index: 463

Text #13

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1569887 (Python Code)

Max Activating Token Index: 350

Text #14

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1493470 (Python Code)

Max Activating Token Index: 116

Text #15

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1627455 (Python Code)

Max Activating Token Index: 777

Text #16

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1631632 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1380125 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1545554 (Python Code)

Max Activating Token Index: 1012

Text #19

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1389719 (Python Code)

Max Activating Token Index: 513