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

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

Neuron 686 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: 0.0719. Min Range: -0.0719

Max Act: 0.0719. Min Act: -0.0002

Data Index: 218519 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1310551 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0624. Min Act: -0.0002

Data Index: 778693 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0665. Min Act: -0.0002

Data Index: 588469 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0574. Min Act: -0.0002

Data Index: 85805 (C4 (Web Text))

Max Activating Token Index: 688

Text #5

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0630. Min Act: -0.0002

Data Index: 755050 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0546. Min Act: -0.0002

Data Index: 7371 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0551. Min Act: -0.0002

Data Index: 315841 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0554. Min Act: -0.0002

Data Index: 942990 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0534. Min Act: -0.0002

Data Index: 904480 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1420220 (Python Code)

Max Activating Token Index: 637

Text #11

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1540351 (Python Code)

Max Activating Token Index: 560

Text #12

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0491. Min Act: -0.0002

Data Index: 1122401 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0464. Min Act: -0.0002

Data Index: 32972 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1268450 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1559303 (Python Code)

Max Activating Token Index: 660

Text #16

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0515. Min Act: -0.0002

Data Index: 757980 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1455185 (Python Code)

Max Activating Token Index: 336

Text #18

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0475. Min Act: -0.0002

Data Index: 420536 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0719. Min Range: -0.0719

Max Act: 0.0494. Min Act: -0.0002

Data Index: 542092 (C4 (Web Text))

Max Activating Token Index: 736