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

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

Neuron 1580 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: 0.0822. Min Range: -0.0822

Max Act: 0.0801. Min Act: -0.0000

Data Index: 42237 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1161440 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0800. Min Act: -0.0001

Data Index: 256163 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0779. Min Act: -0.0001

Data Index: 426954 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0770. Min Act: -0.0001

Data Index: 57872 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0739. Min Act: -0.0002

Data Index: 266358 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0706. Min Act: -0.0002

Data Index: 41749 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1226834 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1246227 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0681. Min Act: -0.0001

Data Index: 290596 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0681. Min Act: -0.0001

Data Index: 365704 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0689. Min Act: -0.0001

Data Index: 467143 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1061093 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0713. Min Act: -0.0000

Data Index: 2580 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0683. Min Act: -0.0002

Data Index: 585929 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0692. Min Act: -0.0002

Data Index: 678806 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0679. Min Act: -0.0001

Data Index: 502933 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0640. Min Act: -0.0002

Data Index: 961889 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1352831 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.0822. Min Range: -0.0822

Max Act: 0.0677. Min Act: -0.0002

Data Index: 949009 (C4 (Web Text))

Max Activating Token Index: 262