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

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

Neuron 2794 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: 1.1746. Min Range: -1.1746

Max Act: 1.1746. Min Act: -0.0000

Data Index: 275563 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 1.1746. Min Range: -1.1746

Max Act: 1.0516. Min Act: -0.0000

Data Index: 684526 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 1.1746. Min Range: -1.1746

Max Act: 1.0227. Min Act: -0.0000

Data Index: 1233653 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9898. Min Act: -0.0000

Data Index: 1128421 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9988. Min Act: -0.0000

Data Index: 337426 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9686. Min Act: -0.0000

Data Index: 313578 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.1746. Min Range: -1.1746

Max Act: 1.0147. Min Act: -0.0000

Data Index: 12231 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1150075 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9239. Min Act: -0.0000

Data Index: 115487 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9796. Min Act: -0.0000

Data Index: 905232 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9602. Min Act: -0.0000

Data Index: 1229128 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9101. Min Act: -0.0000

Data Index: 1319290 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9290. Min Act: -0.0000

Data Index: 707143 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.8949. Min Act: -0.0000

Data Index: 255853 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.8951. Min Act: -0.0000

Data Index: 30232 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9201. Min Act: -0.0000

Data Index: 781903 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9247. Min Act: -0.0000

Data Index: 487737 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1317850 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.8564. Min Act: -0.0000

Data Index: 913779 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.1746. Min Range: -1.1746

Max Act: 0.8674. Min Act: -0.0000

Data Index: 875421 (C4 (Web Text))

Max Activating Token Index: 662