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

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

Neuron 3491 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: 0.8739. Min Range: -0.8739

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1486904 (Python Code)

Max Activating Token Index: 525

Text #1

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1626768 (Python Code)

Max Activating Token Index: 599

Text #2

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1427352 (Python Code)

Max Activating Token Index: 460

Text #3

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1359998 (Python Code)

Max Activating Token Index: 429

Text #4

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1477279 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1491157 (Python Code)

Max Activating Token Index: 452

Text #6

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1454847 (Python Code)

Max Activating Token Index: 600

Text #7

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1485311 (Python Code)

Max Activating Token Index: 558

Text #8

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1429468 (Python Code)

Max Activating Token Index: 539

Text #9

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1465846 (Python Code)

Max Activating Token Index: 293

Text #10

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1400100 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1489080 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1615464 (Python Code)

Max Activating Token Index: 639

Text #13

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1465090 (Python Code)

Max Activating Token Index: 668

Text #14

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1625837 (Python Code)

Max Activating Token Index: 426

Text #15

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1644605 (Python Code)

Max Activating Token Index: 665

Text #16

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1516787 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7738. Min Act: -0.0000

Data Index: 1389500 (Python Code)

Max Activating Token Index: 392

Text #18

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1423576 (Python Code)

Max Activating Token Index: 476

Text #19

Max Range: 0.8739. Min Range: -0.8739

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1578324 (Python Code)

Max Activating Token Index: 243