Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1890 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0718. Min Act: -0.0006

Data Index: 832532 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0542. Min Act: -0.0006

Data Index: 278421 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0571. Min Act: -0.0006

Data Index: 920858 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0552. Min Act: -0.0006

Data Index: 302246 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0498. Min Act: -0.0006

Data Index: 304321 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0544. Min Act: -0.0006

Data Index: 128164 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0575. Min Act: -0.0006

Data Index: 467698 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0526. Min Act: -0.0006

Data Index: 532271 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0513. Min Act: -0.0006

Data Index: 1141181 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0437. Min Act: -0.0006

Data Index: 190997 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0535. Min Act: -0.0006

Data Index: 589013 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0482. Min Act: -0.0006

Data Index: 519753 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0497. Min Act: -0.0006

Data Index: 828447 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0571. Min Act: -0.0006

Data Index: 13221 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0469. Min Act: -0.0006

Data Index: 737182 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0484. Min Act: -0.0006

Data Index: 449798 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0495. Min Act: -0.0006

Data Index: 387058 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0486. Min Act: -0.0006

Data Index: 609809 (C4 (Web Text))

Max Activating Token Index: 580

Text #18

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0473. Min Act: -0.0006

Data Index: 1201352 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0718. Min Range: -0.0718

Max Act: 0.0493. Min Act: -0.0006

Data Index: 384840 (C4 (Web Text))

Max Activating Token Index: 808