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

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

Neuron 3020 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1417627 (Python Code)

Max Activating Token Index: 357

Text #1

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0885. Min Act: -0.0000

Data Index: 272844 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1482687 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0817. Min Act: -0.0000

Data Index: 1486565 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1486805 (Python Code)

Max Activating Token Index: 315

Text #5

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1555290 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0784. Min Act: -0.0000

Data Index: 1600464 (Python Code)

Max Activating Token Index: 899

Text #7

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1035276 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1553479 (Python Code)

Max Activating Token Index: 769

Text #9

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1548815 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1529328 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0734. Min Act: -0.0000

Data Index: 1543209 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0708. Min Act: -0.0000

Data Index: 1477282 (Python Code)

Max Activating Token Index: 907

Text #13

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0731. Min Act: -0.0000

Data Index: 235744 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0682. Min Act: -0.0000

Data Index: 787516 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1492801 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0683. Min Act: -0.0000

Data Index: 216237 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0651. Min Act: -0.0000

Data Index: 380854 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1631135 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 0.1002. Min Range: -0.1002

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1638515 (Python Code)

Max Activating Token Index: 652