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

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

Neuron 5480 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: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0001

Data Index: 518629 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0458. Min Act: -0.0001

Data Index: 1060797 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0441. Min Act: -0.0001

Data Index: 628103 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1539985 (Python Code)

Max Activating Token Index: 611

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0462. Min Act: -0.0001

Data Index: 1396685 (Python Code)

Max Activating Token Index: 705

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1456241 (Python Code)

Max Activating Token Index: 285

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1442489 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1272475 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0401. Min Act: -0.0001

Data Index: 740938 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1559848 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1550271 (Python Code)

Max Activating Token Index: 907

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0398. Min Act: -0.0001

Data Index: 1443678 (Python Code)

Max Activating Token Index: 610

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0398. Min Act: -0.0001

Data Index: 859527 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1645427 (Python Code)

Max Activating Token Index: 622

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0395. Min Act: -0.0001

Data Index: 1515009 (Python Code)

Max Activating Token Index: 612

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0376. Min Act: -0.0001

Data Index: 293212 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0375. Min Act: -0.0001

Data Index: 710048 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1402165 (Python Code)

Max Activating Token Index: 992

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1639892 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0379. Min Act: -0.0001

Data Index: 1465760 (Python Code)

Max Activating Token Index: 650