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

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

Neuron 1392 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0003

Data Index: 191980 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0696. Min Act: -0.0003

Data Index: 413748 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0670. Min Act: -0.0003

Data Index: 527418 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0606. Min Act: -0.0003

Data Index: 309095 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1151136 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1298318 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0691. Min Act: -0.0003

Data Index: 850428 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0691. Min Act: -0.0003

Data Index: 839454 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1293648 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0619. Min Act: -0.0003

Data Index: 333739 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0691. Min Act: -0.0003

Data Index: 626454 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1085096 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0528. Min Act: -0.0003

Data Index: 552366 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0612. Min Act: -0.0003

Data Index: 220111 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1040224 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0502. Min Act: -0.0003

Data Index: 762831 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0584. Min Act: -0.0003

Data Index: 227956 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0605. Min Act: -0.0003

Data Index: 662084 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1108539 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0579. Min Act: -0.0003

Data Index: 943617 (C4 (Web Text))

Max Activating Token Index: 176