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

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

Neuron 3289 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1533679 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1505573 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1497246 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1633921 (Python Code)

Max Activating Token Index: 864

Text #4

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0975. Min Act: -0.0001

Data Index: 301555 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1622930 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1498034 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1539589 (Python Code)

Max Activating Token Index: 334

Text #8

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1622166 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1651231 (Python Code)

Max Activating Token Index: 720

Text #10

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0798. Min Act: -0.0001

Data Index: 738094 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1588470 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0777. Min Act: -0.0001

Data Index: 1564234 (Python Code)

Max Activating Token Index: 300

Text #13

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0845. Min Act: -0.0001

Data Index: 1625170 (Python Code)

Max Activating Token Index: 992

Text #14

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0688. Min Act: -0.0001

Data Index: 550409 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1613926 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0639. Min Act: -0.0000

Data Index: 1439456 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0707. Min Act: -0.0001

Data Index: 4567 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0714. Min Act: -0.0001

Data Index: 710274 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.1225. Min Range: -0.1225

Max Act: 0.0718. Min Act: -0.0000

Data Index: 1610331 (Python Code)

Max Activating Token Index: 55