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

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

Neuron 3006 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1416480 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1550951 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1589396 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1442898 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5966. Min Act: -0.0000

Data Index: 1576292 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1431801 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1512322 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1395649 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1546627 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1543923 (Python Code)

Max Activating Token Index: 39

Text #10

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1378689 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1374363 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1486580 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5370. Min Act: -0.0000

Data Index: 1629346 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1524596 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1605486 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1604562 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1602035 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1576438 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1534068 (Python Code)

Max Activating Token Index: 23