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

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

Neuron 3592 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.2615. Min Act: -0.0000

Data Index: 1368573 (Python Code)

Max Activating Token Index: 806

Text #1

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.2540. Min Act: -0.0000

Data Index: 357003 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.2120. Min Act: -0.0000

Data Index: 1649862 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1051321 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.1927. Min Act: -0.0000

Data Index: 1394293 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.2512. Min Act: -0.0000

Data Index: 1500614 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.1745. Min Act: -0.0000

Data Index: 1513963 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1464391 (Python Code)

Max Activating Token Index: 558

Text #8

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1393755 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 1.2615. Min Range: -1.2615

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1532387 (Python Code)

Max Activating Token Index: 461

Text #10

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.1017. Min Act: -0.0000

Data Index: 1375406 (Python Code)

Max Activating Token Index: 1002

Text #11

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1640669 (Python Code)

Max Activating Token Index: 586

Text #12

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.0889. Min Act: -0.0000

Data Index: 733 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.0220. Min Act: -0.0000

Data Index: 165912 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.0593. Min Act: -0.0000

Data Index: 1525495 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1552174 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 1.2615. Min Range: -1.2615

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1446066 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 1.2615. Min Range: -1.2615

Max Act: 0.9688. Min Act: -0.0000

Data Index: 825710 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 1.2615. Min Range: -1.2615

Max Act: 0.9739. Min Act: -0.0000

Data Index: 1637409 (Python Code)

Max Activating Token Index: 999

Text #19

Max Range: 1.2615. Min Range: -1.2615

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1375955 (Python Code)

Max Activating Token Index: 761