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

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

Neuron 218 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: 0.2197. Min Range: -0.2197

Max Act: 0.2192. Min Act: -0.0002

Data Index: 234124 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.2095. Min Act: -0.0001

Data Index: 1222334 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.2197. Min Act: -0.0001

Data Index: 726290 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1070545 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1967. Min Act: -0.0001

Data Index: 131814 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1935. Min Act: -0.0002

Data Index: 283626 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1914. Min Act: -0.0001

Data Index: 137236 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1871. Min Act: -0.0002

Data Index: 1224540 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1746. Min Act: -0.0001

Data Index: 760406 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1777. Min Act: -0.0002

Data Index: 911143 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1777. Min Act: -0.0002

Data Index: 472533 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1753. Min Act: -0.0001

Data Index: 454900 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1788. Min Act: -0.0002

Data Index: 632195 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1724. Min Act: -0.0001

Data Index: 626837 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1720. Min Act: -0.0002

Data Index: 1047177 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1713. Min Act: -0.0002

Data Index: 42603 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1707. Min Act: -0.0002

Data Index: 415993 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1754. Min Act: -0.0001

Data Index: 285625 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1628. Min Act: -0.0002

Data Index: 1039234 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.2197. Min Range: -0.2197

Max Act: 0.1677. Min Act: -0.0002

Data Index: 354797 (C4 (Web Text))

Max Activating Token Index: 91