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

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

Neuron 2482 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5915. Min Range: -4.5915

Max Act: 4.5915. Min Act: -0.0000

Data Index: 1635814 (Python Code)

Max Activating Token Index: 673

Text #1

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.6386. Min Act: -0.0000

Data Index: 210878 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 4.5915. Min Range: -4.5915

Max Act: 3.9804. Min Act: -0.0000

Data Index: 93730 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1640244 (Python Code)

Max Activating Token Index: 527

Text #4

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1130233 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1581070 (Python Code)

Max Activating Token Index: 488

Text #6

Max Range: 4.5915. Min Range: -4.5915

Max Act: 1.3222. Min Act: -0.0000

Data Index: 1404617 (Python Code)

Max Activating Token Index: 66

Text #7

Max Range: 4.5915. Min Range: -4.5915

Max Act: 1.1517. Min Act: -0.0000

Data Index: 1516206 (Python Code)

Max Activating Token Index: 972

Text #8

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.5230. Min Act: -0.0000

Data Index: 601507 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.3573. Min Act: -0.0000

Data Index: 1556150 (Python Code)

Max Activating Token Index: 372

Text #10

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.2087. Min Act: -0.0000

Data Index: 533419 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1488111 (Python Code)

Max Activating Token Index: 367

Text #12

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.1832. Min Act: -0.0000

Data Index: 220036 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.1389. Min Act: -0.0000

Data Index: 1447537 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1413715 (Python Code)

Max Activating Token Index: 678

Text #15

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1547204 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1380353 (Python Code)

Max Activating Token Index: 869

Text #17

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.1918. Min Act: -0.0000

Data Index: 361841 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.1456. Min Act: -0.0000

Data Index: 964380 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 4.5915. Min Range: -4.5915

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1017610 (C4 (Web Text))

Max Activating Token Index: 189