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

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

Neuron 1506 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0550. Min Act: -0.0002

Data Index: 158082 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0002

Data Index: 225866 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0564. Min Act: -0.0002

Data Index: 614056 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1315444 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1206317 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1271535 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1346494 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0511. Min Act: -0.0002

Data Index: 156373 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1148606 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1056355 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0528. Min Act: -0.0002

Data Index: 616882 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0517. Min Act: -0.0002

Data Index: 432045 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0482. Min Act: -0.0002

Data Index: 424893 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0495. Min Act: -0.0002

Data Index: 925464 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0509. Min Act: -0.0002

Data Index: 789694 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0505. Min Act: -0.0002

Data Index: 283329 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0501. Min Act: -0.0002

Data Index: 496520 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0503. Min Act: -0.0002

Data Index: 133084 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0512. Min Act: -0.0002

Data Index: 833749 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0515. Min Act: -0.0002

Data Index: 31758 (C4 (Web Text))

Max Activating Token Index: 359