Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 342 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.1219. Min Act: -0.0001

Data Index: 340472 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0815. Min Act: -0.0001

Data Index: 333172 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0741. Min Act: -0.0001

Data Index: 634301 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0743. Min Act: -0.0001

Data Index: 973205 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0689. Min Act: -0.0000

Data Index: 749990 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0740. Min Act: -0.0001

Data Index: 778398 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0715. Min Act: -0.0001

Data Index: 549844 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1252558 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1213218 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1091379 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1342310 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0666. Min Act: -0.0001

Data Index: 503808 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0682. Min Act: -0.0001

Data Index: 398484 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0669. Min Act: -0.0001

Data Index: 913725 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1035650 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1276107 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1198090 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0644. Min Act: -0.0001

Data Index: 908030 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0620. Min Act: -0.0001

Data Index: 7809 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.1219. Min Range: -0.1219

Max Act: 0.0662. Min Act: -0.0001

Data Index: 99814 (C4 (Web Text))

Max Activating Token Index: 675