Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1655 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0850. Min Act: -0.0002

Data Index: 217557 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0820. Min Act: -0.0002

Data Index: 151556 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0828. Min Act: -0.0002

Data Index: 547181 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0822. Min Act: -0.0002

Data Index: 216846 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1005181 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1001533 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0769. Min Act: -0.0002

Data Index: 865162 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0713. Min Act: -0.0002

Data Index: 930876 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0775. Min Act: -0.0002

Data Index: 820332 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0756. Min Act: -0.0002

Data Index: 517132 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0728. Min Act: -0.0002

Data Index: 220147 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1042629 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0761. Min Act: -0.0002

Data Index: 406612 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1312808 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0742. Min Act: -0.0002

Data Index: 436857 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0730. Min Act: -0.0002

Data Index: 325768 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0728. Min Act: -0.0002

Data Index: 775550 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0735. Min Act: -0.0002

Data Index: 1169415 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0723. Min Act: -0.0002

Data Index: 952346 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 0.0850. Min Range: -0.0850

Max Act: 0.0750. Min Act: -0.0002

Data Index: 631525 (C4 (Web Text))

Max Activating Token Index: 768