Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 732 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1790. Min Act: -0.0001

Data Index: 1571584 (Python Code)

Max Activating Token Index: 595

Text #1

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1984. Min Act: -0.0001

Data Index: 1373958 (Python Code)

Max Activating Token Index: 822

Text #2

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.3715. Min Act: -0.0001

Data Index: 1559426 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1294. Min Act: -0.0001

Data Index: 1418955 (Python Code)

Max Activating Token Index: 774

Text #4

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0888. Min Act: -0.0001

Data Index: 1528350 (Python Code)

Max Activating Token Index: 782

Text #5

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2421. Min Act: -0.0001

Data Index: 1396917 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2010. Min Act: -0.0001

Data Index: 1519991 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1521. Min Act: -0.0001

Data Index: 1371656 (Python Code)

Max Activating Token Index: 538

Text #8

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1006. Min Act: -0.0001

Data Index: 1389882 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0514. Min Act: -0.0001

Data Index: 1378915 (Python Code)

Max Activating Token Index: 636

Text #10

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2406. Min Act: -0.0001

Data Index: 1477153 (Python Code)

Max Activating Token Index: 607

Text #11

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1012. Min Act: -0.0001

Data Index: 1557524 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.2286. Min Act: -0.0001

Data Index: 1653087 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9884. Min Act: -0.0001

Data Index: 1400873 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0795. Min Act: -0.0001

Data Index: 1365159 (Python Code)

Max Activating Token Index: 60

Text #15

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0989. Min Act: -0.0001

Data Index: 1504857 (Python Code)

Max Activating Token Index: 551

Text #16

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1577038 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.0648. Min Act: -0.0001

Data Index: 1627354 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 1.3715. Min Range: -1.3715

Max Act: 1.1382. Min Act: -0.0001

Data Index: 1387484 (Python Code)

Max Activating Token Index: 641

Text #19

Max Range: 1.3715. Min Range: -1.3715

Max Act: 0.9984. Min Act: -0.0001

Data Index: 1477352 (Python Code)

Max Activating Token Index: 65