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

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

Neuron 2942 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4329. Min Range: -2.4329

Max Act: 2.4329. Min Act: -0.0001

Data Index: 1622308 (Python Code)

Max Activating Token Index: 690

Text #1

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.5818. Min Act: -0.0001

Data Index: 1460532 (Python Code)

Max Activating Token Index: 214

Text #2

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.5737. Min Act: -0.0001

Data Index: 1480427 (Python Code)

Max Activating Token Index: 186

Text #3

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.6425. Min Act: -0.0001

Data Index: 1481898 (Python Code)

Max Activating Token Index: 931

Text #4

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.7362. Min Act: -0.0001

Data Index: 1443263 (Python Code)

Max Activating Token Index: 357

Text #5

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.6966. Min Act: -0.0000

Data Index: 1643765 (Python Code)

Max Activating Token Index: 574

Text #6

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.6632. Min Act: -0.0001

Data Index: 1553029 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.6627. Min Act: -0.0001

Data Index: 1608301 (Python Code)

Max Activating Token Index: 24

Text #8

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.6277. Min Act: -0.0001

Data Index: 1585621 (Python Code)

Max Activating Token Index: 595

Text #9

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1582600 (Python Code)

Max Activating Token Index: 170

Text #10

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.5440. Min Act: -0.0001

Data Index: 1609045 (Python Code)

Max Activating Token Index: 293

Text #11

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.5777. Min Act: -0.0000

Data Index: 1529972 (Python Code)

Max Activating Token Index: 825

Text #12

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.5305. Min Act: -0.0000

Data Index: 1640861 (Python Code)

Max Activating Token Index: 463

Text #13

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.6695. Min Act: -0.0001

Data Index: 1592646 (Python Code)

Max Activating Token Index: 605

Text #14

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.4272. Min Act: -0.0000

Data Index: 1398760 (Python Code)

Max Activating Token Index: 744

Text #15

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.5342. Min Act: -0.0001

Data Index: 1397508 (Python Code)

Max Activating Token Index: 691

Text #16

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.4351. Min Act: -0.0001

Data Index: 1398667 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.5231. Min Act: -0.0001

Data Index: 1388333 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.3887. Min Act: -0.0001

Data Index: 1567229 (Python Code)

Max Activating Token Index: 453

Text #19

Max Range: 2.4329. Min Range: -2.4329

Max Act: 1.3692. Min Act: -0.0000

Data Index: 1495508 (Python Code)

Max Activating Token Index: 104