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

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

Neuron 860 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: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1093292 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1002. Min Act: -0.0000

Data Index: 690882 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1102719 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0922. Min Act: -0.0000

Data Index: 279893 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0897. Min Act: -0.0000

Data Index: 43883 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0865. Min Act: -0.0000

Data Index: 794309 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0828. Min Act: -0.0000

Data Index: 368522 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0839. Min Act: -0.0000

Data Index: 165793 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0824. Min Act: -0.0000

Data Index: 751133 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0819. Min Act: -0.0000

Data Index: 460047 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0788. Min Act: -0.0000

Data Index: 787244 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0815. Min Act: -0.0000

Data Index: 3006 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0797. Min Act: -0.0000

Data Index: 453666 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0741. Min Act: -0.0000

Data Index: 1168515 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1525388 (Python Code)

Max Activating Token Index: 484

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0801. Min Act: -0.0000

Data Index: 369469 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0740. Min Act: -0.0000

Data Index: 544379 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0781. Min Act: -0.0000

Data Index: 1044543 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0712. Min Act: -0.0000

Data Index: 538472 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0708. Min Act: -0.0001

Data Index: 247202 (C4 (Web Text))

Max Activating Token Index: 949