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

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

Neuron 2252 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.1109. Min Act: -0.0000

Data Index: 114547 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0863. Min Act: -0.0000

Data Index: 734908 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0853. Min Act: -0.0000

Data Index: 147333 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0840. Min Act: -0.0000

Data Index: 448795 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0801. Min Act: -0.0000

Data Index: 903175 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0728. Min Act: -0.0000

Data Index: 836514 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0778. Min Act: -0.0000

Data Index: 613342 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1529432 (Python Code)

Max Activating Token Index: 532

Text #8

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0831. Min Act: -0.0000

Data Index: 208361 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0828. Min Act: -0.0000

Data Index: 74179 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1302153 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0788. Min Act: -0.0000

Data Index: 223304 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0724. Min Act: -0.0000

Data Index: 591216 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0645. Min Act: -0.0000

Data Index: 925728 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0675. Min Act: -0.0000

Data Index: 34644 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0671. Min Act: -0.0000

Data Index: 1372397 (Python Code)

Max Activating Token Index: 155

Text #16

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1120195 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0747. Min Act: -0.0000

Data Index: 1179440 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1080627 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.1109. Min Range: -0.1109

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1008474 (C4 (Web Text))

Max Activating Token Index: 583