Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1564 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0003

Data Index: 235088 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1193786 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1548958 (Python Code)

Max Activating Token Index: 528

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0643. Min Act: -0.0003

Data Index: 616926 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1249684 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0615. Min Act: -0.0003

Data Index: 884766 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0610. Min Act: -0.0003

Data Index: 680359 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0619. Min Act: -0.0003

Data Index: 192521 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0598. Min Act: -0.0003

Data Index: 954738 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1609398 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0594. Min Act: -0.0003

Data Index: 715496 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0580. Min Act: -0.0003

Data Index: 670444 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1439348 (Python Code)

Max Activating Token Index: 85

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1539742 (Python Code)

Max Activating Token Index: 677

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0581. Min Act: -0.0003

Data Index: 162519 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0582. Min Act: -0.0003

Data Index: 927519 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0587. Min Act: -0.0003

Data Index: 705328 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0584. Min Act: -0.0003

Data Index: 978591 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1639363 (Python Code)

Max Activating Token Index: 802

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0557. Min Act: -0.0003

Data Index: 1490252 (Python Code)

Max Activating Token Index: 518