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

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

Neuron 28 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: 2.2554. Min Range: -2.2554

Max Act: 2.1997. Min Act: -0.0000

Data Index: 1571542 (Python Code)

Max Activating Token Index: 206

Text #1

Max Range: 2.2554. Min Range: -2.2554

Max Act: 2.2554. Min Act: -0.0000

Data Index: 1450106 (Python Code)

Max Activating Token Index: 704

Text #2

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.8852. Min Act: -0.0000

Data Index: 1176131 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.9606. Min Act: -0.0000

Data Index: 1618699 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.9204. Min Act: -0.0000

Data Index: 1379476 (Python Code)

Max Activating Token Index: 587

Text #5

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.9230. Min Act: -0.0000

Data Index: 1625702 (Python Code)

Max Activating Token Index: 720

Text #6

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1510892 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.8475. Min Act: -0.0000

Data Index: 1550493 (Python Code)

Max Activating Token Index: 712

Text #8

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1414615 (Python Code)

Max Activating Token Index: 242

Text #9

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.8225. Min Act: -0.0000

Data Index: 1534689 (Python Code)

Max Activating Token Index: 448

Text #10

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.7714. Min Act: -0.0000

Data Index: 1613545 (Python Code)

Max Activating Token Index: 159

Text #11

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.7184. Min Act: -0.0000

Data Index: 1450803 (Python Code)

Max Activating Token Index: 287

Text #12

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.7562. Min Act: -0.0000

Data Index: 1612476 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.7152. Min Act: -0.0000

Data Index: 1455967 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.7049. Min Act: -0.0000

Data Index: 1550812 (Python Code)

Max Activating Token Index: 995

Text #15

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.7420. Min Act: -0.0000

Data Index: 1517073 (Python Code)

Max Activating Token Index: 680

Text #16

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1499859 (Python Code)

Max Activating Token Index: 201

Text #17

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.5645. Min Act: -0.0000

Data Index: 1511901 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.6689. Min Act: -0.0000

Data Index: 1650144 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 2.2554. Min Range: -2.2554

Max Act: 1.6200. Min Act: -0.0000

Data Index: 1455613 (Python Code)

Max Activating Token Index: 831