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

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

Neuron 1257 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: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0003

Data Index: 727131 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0612. Min Act: -0.0003

Data Index: 1346950 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0486. Min Act: -0.0003

Data Index: 790292 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0551. Min Act: -0.0003

Data Index: 738089 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0584. Min Act: -0.0003

Data Index: 196067 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0588. Min Act: -0.0003

Data Index: 221858 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1189502 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1197389 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0516. Min Act: -0.0003

Data Index: 665141 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0567. Min Act: -0.0003

Data Index: 591499 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0611. Min Act: -0.0003

Data Index: 978213 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0526. Min Act: -0.0003

Data Index: 306966 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0535. Min Act: -0.0003

Data Index: 721728 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0513. Min Act: -0.0003

Data Index: 105484 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0527. Min Act: -0.0003

Data Index: 781788 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0516. Min Act: -0.0003

Data Index: 407932 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0546. Min Act: -0.0003

Data Index: 837408 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0606. Min Act: -0.0003

Data Index: 405136 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1190713 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0498. Min Act: -0.0003

Data Index: 1117690 (C4 (Web Text))

Max Activating Token Index: 711