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

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

Neuron 4108 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: 0.0902. Min Range: -0.0902

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1656441 (Python Code)

Max Activating Token Index: 482

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1317614 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1411034 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1156454 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1269379 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0789. Min Act: -0.0002

Data Index: 1523694 (Python Code)

Max Activating Token Index: 148

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1628087 (Python Code)

Max Activating Token Index: 212

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1548130 (Python Code)

Max Activating Token Index: 328

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1500742 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0748. Min Act: -0.0002

Data Index: 958210 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1585840 (Python Code)

Max Activating Token Index: 599

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1640137 (Python Code)

Max Activating Token Index: 618

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0855. Min Act: -0.0002

Data Index: 674445 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1122631 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0748. Min Act: -0.0002

Data Index: 313934 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0770. Min Act: -0.0002

Data Index: 548199 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1615090 (Python Code)

Max Activating Token Index: 278

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0759. Min Act: -0.0002

Data Index: 404222 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1556390 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0732. Min Act: -0.0002

Data Index: 82003 (C4 (Web Text))

Max Activating Token Index: 8