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

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

Neuron 4192 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6759. Min Act: -0.0002

Data Index: 1395063 (Python Code)

Max Activating Token Index: 720

Text #1

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6585. Min Act: -0.0002

Data Index: 1515618 (Python Code)

Max Activating Token Index: 814

Text #2

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6741. Min Act: -0.0002

Data Index: 498160 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6029. Min Act: -0.0002

Data Index: 1621902 (Python Code)

Max Activating Token Index: 296

Text #4

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5066. Min Act: -0.0002

Data Index: 1412691 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5483. Min Act: -0.0002

Data Index: 1357675 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5568. Min Act: -0.0002

Data Index: 1438222 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6436. Min Act: -0.0002

Data Index: 1490627 (Python Code)

Max Activating Token Index: 869

Text #8

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5754. Min Act: -0.0002

Data Index: 1638517 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5661. Min Act: -0.0002

Data Index: 236508 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4909. Min Act: -0.0002

Data Index: 1427703 (Python Code)

Max Activating Token Index: 138

Text #11

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.4913. Min Act: -0.0002

Data Index: 1623455 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.6526. Min Act: -0.0002

Data Index: 1632077 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5753. Min Act: -0.0002

Data Index: 33976 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5526. Min Act: -0.0002

Data Index: 867518 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5255. Min Act: -0.0002

Data Index: 1497261 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5240. Min Act: -0.0002

Data Index: 1571591 (Python Code)

Max Activating Token Index: 1001

Text #17

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5544. Min Act: -0.0002

Data Index: 957916 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5535. Min Act: -0.0002

Data Index: 57668 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.6759. Min Range: -0.6759

Max Act: 0.5772. Min Act: -0.0002

Data Index: 1632508 (Python Code)

Max Activating Token Index: 740