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

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

Neuron 1688 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5806. Min Act: 0.0000

Data Index: 1114283 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1166597 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5306. Min Act: -0.0000

Data Index: 76090 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5286. Min Act: -0.0000

Data Index: 567259 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5284. Min Act: -0.0000

Data Index: 16573 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1341805 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5123. Min Act: -0.0000

Data Index: 586033 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5279. Min Act: -0.0000

Data Index: 721521 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5090. Min Act: -0.0000

Data Index: 504713 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5133. Min Act: -0.0000

Data Index: 831257 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1211828 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.4754. Min Act: -0.0000

Data Index: 183611 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.4902. Min Act: -0.0000

Data Index: 408681 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.5024. Min Act: -0.0000

Data Index: 665295 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.4870. Min Act: -0.0000

Data Index: 788455 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.4730. Min Act: -0.0000

Data Index: 837751 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.4986. Min Act: -0.0000

Data Index: 233347 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.4867. Min Act: -0.0000

Data Index: 140201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.4858. Min Act: -0.0000

Data Index: 277900 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.5806. Min Range: -0.5806

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1072854 (C4 (Web Text))

Max Activating Token Index: 125