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

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

Neuron 5050 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1421233 (Python Code)

Max Activating Token Index: 1013

Text #1

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1401781 (Python Code)

Max Activating Token Index: 841

Text #2

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1603029 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1645637 (Python Code)

Max Activating Token Index: 694

Text #4

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0783. Min Act: -0.0001

Data Index: 571473 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1473582 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1588839 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0752. Min Act: -0.0001

Data Index: 290540 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1500251 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1049287 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0691. Min Act: -0.0001

Data Index: 431296 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1570009 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1628152 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0670. Min Act: -0.0001

Data Index: 400070 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0704. Min Act: -0.0001

Data Index: 1588472 (Python Code)

Max Activating Token Index: 442

Text #15

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1652281 (Python Code)

Max Activating Token Index: 571

Text #16

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1410223 (Python Code)

Max Activating Token Index: 204

Text #17

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0668. Min Act: -0.0001

Data Index: 181469 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1534330 (Python Code)

Max Activating Token Index: 190

Text #19

Max Range: 0.0893. Min Range: -0.0893

Max Act: 0.0639. Min Act: -0.0001

Data Index: 725418 (C4 (Web Text))

Max Activating Token Index: 82