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

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

Neuron 4670 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: 0.7667. Min Range: -0.7667

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1628904 (Python Code)

Max Activating Token Index: 871

Text #1

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1486209 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1590857 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1485711 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1566606 (Python Code)

Max Activating Token Index: 808

Text #5

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1574032 (Python Code)

Max Activating Token Index: 352

Text #6

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5565. Min Act: -0.0000

Data Index: 1406226 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1483512 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1505893 (Python Code)

Max Activating Token Index: 130

Text #9

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1594997 (Python Code)

Max Activating Token Index: 631

Text #10

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1413734 (Python Code)

Max Activating Token Index: 819

Text #11

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5197. Min Act: -0.0001

Data Index: 1518896 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1472697 (Python Code)

Max Activating Token Index: 949

Text #13

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1605943 (Python Code)

Max Activating Token Index: 722

Text #14

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1591108 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1574055 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6335. Min Act: -0.0000

Data Index: 1525535 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1528502 (Python Code)

Max Activating Token Index: 583

Text #18

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1526050 (Python Code)

Max Activating Token Index: 460

Text #19

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1553388 (Python Code)

Max Activating Token Index: 608