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

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

Neuron 5792 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1528853 (Python Code)

Max Activating Token Index: 217

Text #1

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1542312 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1537654 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1627940 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3812. Min Act: -0.0000

Data Index: 706449 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3709. Min Act: -0.0000

Data Index: 1650315 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3825. Min Act: -0.0000

Data Index: 1555879 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1374655 (Python Code)

Max Activating Token Index: 18

Text #8

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3419. Min Act: -0.0000

Data Index: 1475431 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1609878 (Python Code)

Max Activating Token Index: 82

Text #10

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3311. Min Act: -0.0000

Data Index: 28948 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1635682 (Python Code)

Max Activating Token Index: 860

Text #12

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3373. Min Act: -0.0000

Data Index: 1651110 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3203. Min Act: -0.0000

Data Index: 50148 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3372. Min Act: -0.0001

Data Index: 788192 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1197019 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3533. Min Act: -0.0000

Data Index: 92020 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1596707 (Python Code)

Max Activating Token Index: 503

Text #18

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3371. Min Act: -0.0000

Data Index: 501434 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.4421. Min Range: -0.4421

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1452483 (Python Code)

Max Activating Token Index: 70