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

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

Neuron 4748 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: 1.3442. Min Range: -1.3442

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1556816 (Python Code)

Max Activating Token Index: 270

Text #1

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1487. Min Act: -0.0000

Data Index: 1392980 (Python Code)

Max Activating Token Index: 848

Text #2

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1165. Min Act: -0.0000

Data Index: 1454661 (Python Code)

Max Activating Token Index: 406

Text #3

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1545693 (Python Code)

Max Activating Token Index: 43

Text #4

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1458530 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 1.3442. Min Range: -1.3442

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1373877 (Python Code)

Max Activating Token Index: 455

Text #6

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1517818 (Python Code)

Max Activating Token Index: 179

Text #7

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1625694 (Python Code)

Max Activating Token Index: 490

Text #8

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1526138 (Python Code)

Max Activating Token Index: 680

Text #9

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1513303 (Python Code)

Max Activating Token Index: 113

Text #10

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1557935 (Python Code)

Max Activating Token Index: 171

Text #11

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1647456 (Python Code)

Max Activating Token Index: 191

Text #12

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1395495 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.8916. Min Act: -0.0000

Data Index: 1603669 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1580552 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1450014 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1507039 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1389550 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1475702 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 1.3442. Min Range: -1.3442

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1463707 (Python Code)

Max Activating Token Index: 970