Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2477 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1406637 (Python Code)

Max Activating Token Index: 791

Text #1

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0775. Min Act: -0.0001

Data Index: 798773 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0707. Min Act: -0.0000

Data Index: 624837 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1644311 (Python Code)

Max Activating Token Index: 614

Text #4

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0552. Min Act: -0.0001

Data Index: 1527606 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0590. Min Act: -0.0001

Data Index: 535610 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0571. Min Act: 0.0000

Data Index: 752664 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0562. Min Act: -0.0001

Data Index: 664097 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0541. Min Act: -0.0000

Data Index: 495162 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1363663 (Python Code)

Max Activating Token Index: 488

Text #10

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1632401 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1537889 (Python Code)

Max Activating Token Index: 747

Text #12

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1649270 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0525. Min Act: -0.0000

Data Index: 1184384 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0509. Min Act: -0.0001

Data Index: 1582632 (Python Code)

Max Activating Token Index: 307

Text #15

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1467167 (Python Code)

Max Activating Token Index: 942

Text #16

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0488. Min Act: -0.0001

Data Index: 1553059 (Python Code)

Max Activating Token Index: 971

Text #17

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1391227 (Python Code)

Max Activating Token Index: 179

Text #18

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1498270 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 0.0918. Min Range: -0.0918

Max Act: 0.0505. Min Act: -0.0001

Data Index: 1411902 (Python Code)

Max Activating Token Index: 493