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

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

Neuron 1643 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.4413. Min Act: -0.0000

Data Index: 1422598 (Python Code)

Max Activating Token Index: 865

Text #1

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.3174. Min Act: -0.0000

Data Index: 1445685 (Python Code)

Max Activating Token Index: 531

Text #2

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.3969. Min Act: -0.0000

Data Index: 1440727 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.3832. Min Act: -0.0000

Data Index: 1464580 (Python Code)

Max Activating Token Index: 444

Text #4

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.1531. Min Act: -0.0000

Data Index: 1514451 (Python Code)

Max Activating Token Index: 722

Text #5

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.3764. Min Act: -0.0000

Data Index: 1443236 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.2499. Min Act: -0.0000

Data Index: 1487641 (Python Code)

Max Activating Token Index: 1018

Text #7

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.0971. Min Act: -0.0000

Data Index: 360524 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.3339. Min Act: -0.0000

Data Index: 1518233 (Python Code)

Max Activating Token Index: 159

Text #9

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.1958. Min Act: -0.0000

Data Index: 994629 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.1719. Min Act: -0.0000

Data Index: 1452611 (Python Code)

Max Activating Token Index: 881

Text #11

Max Range: 2.4413. Min Range: -2.4413

Max Act: 1.6239. Min Act: -0.0000

Data Index: 1591699 (Python Code)

Max Activating Token Index: 773

Text #12

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.1336. Min Act: -0.0000

Data Index: 1501882 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.1506. Min Act: -0.0000

Data Index: 668588 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.1314. Min Act: -0.0000

Data Index: 1519590 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.1346. Min Act: -0.0000

Data Index: 1534056 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.0998. Min Act: -0.0000

Data Index: 719406 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.0806. Min Act: -0.0000

Data Index: 526880 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 2.4413. Min Range: -2.4413

Max Act: 2.0546. Min Act: -0.0000

Data Index: 1622003 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 2.4413. Min Range: -2.4413

Max Act: 1.9369. Min Act: -0.0000

Data Index: 1634120 (Python Code)

Max Activating Token Index: 60