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

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

Neuron 373 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0691. Min Act: -0.0004

Data Index: 272810 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0004

Data Index: 1024959 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0687. Min Act: -0.0004

Data Index: 308813 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0683. Min Act: -0.0004

Data Index: 750679 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0671. Min Act: -0.0004

Data Index: 469267 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0694. Min Act: -0.0004

Data Index: 1072906 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0689. Min Act: -0.0004

Data Index: 225050 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0690. Min Act: -0.0004

Data Index: 751665 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0696. Min Act: -0.0004

Data Index: 821587 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0682. Min Act: -0.0004

Data Index: 567081 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0644. Min Act: -0.0004

Data Index: 1094636 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0682. Min Act: -0.0004

Data Index: 298955 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0703. Min Act: -0.0004

Data Index: 1225225 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0636. Min Act: -0.0004

Data Index: 1415351 (Python Code)

Max Activating Token Index: 614

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0667. Min Act: -0.0004

Data Index: 917056 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0640. Min Act: -0.0004

Data Index: 736381 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0617. Min Act: -0.0004

Data Index: 1144834 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0640. Min Act: -0.0004

Data Index: 194819 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0632. Min Act: -0.0004

Data Index: 1181817 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0623. Min Act: -0.0004

Data Index: 1253375 (C4 (Web Text))

Max Activating Token Index: 892