Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 643 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.7611. Min Act: -0.0001

Data Index: 1180943 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1062305 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.6653. Min Act: -0.0001

Data Index: 1649765 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.6891. Min Act: -0.0001

Data Index: 1426903 (Python Code)

Max Activating Token Index: 781

Text #4

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.6251. Min Act: -0.0001

Data Index: 777116 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1412096 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.6072. Min Act: -0.0001

Data Index: 1642002 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.6224. Min Act: -0.0000

Data Index: 173541 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5984. Min Act: -0.0001

Data Index: 1510560 (Python Code)

Max Activating Token Index: 680

Text #9

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5698. Min Act: -0.0001

Data Index: 755288 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5651. Min Act: -0.0001

Data Index: 1623522 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1629247 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5544. Min Act: -0.0001

Data Index: 1577896 (Python Code)

Max Activating Token Index: 457

Text #13

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5383. Min Act: -0.0001

Data Index: 1576223 (Python Code)

Max Activating Token Index: 648

Text #14

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5621. Min Act: -0.0001

Data Index: 641640 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5610. Min Act: -0.0001

Data Index: 1399731 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1497935 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5493. Min Act: -0.0000

Data Index: 179748 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5278. Min Act: -0.0001

Data Index: 1459814 (Python Code)

Max Activating Token Index: 591

Text #19

Max Range: 0.7611. Min Range: -0.7611

Max Act: 0.5169. Min Act: -0.0000

Data Index: 948481 (C4 (Web Text))

Max Activating Token Index: 658