Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 901 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0725. Min Act: -0.0002

Data Index: 407744 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1233188 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0734. Min Act: -0.0002

Data Index: 273801 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0695. Min Act: -0.0002

Data Index: 330068 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1192831 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0687. Min Act: -0.0002

Data Index: 280660 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1020463 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0677. Min Act: -0.0002

Data Index: 155845 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0645. Min Act: -0.0002

Data Index: 182190 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0616. Min Act: -0.0002

Data Index: 130098 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0639. Min Act: -0.0002

Data Index: 246104 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1106424 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0606. Min Act: -0.0002

Data Index: 523425 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1176016 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1156231 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0643. Min Act: -0.0002

Data Index: 794096 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1017849 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0640. Min Act: -0.0002

Data Index: 433641 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1061439 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0611. Min Act: -0.0002

Data Index: 76894 (C4 (Web Text))

Max Activating Token Index: 678