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

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

Neuron 3555 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1482397 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0748. Min Act: -0.0000

Data Index: 1613454 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1635436 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0582. Min Act: -0.0000

Data Index: 1576151 (Python Code)

Max Activating Token Index: 512

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0554. Min Act: -0.0000

Data Index: 788786 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1328121 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1419106 (Python Code)

Max Activating Token Index: 432

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0539. Min Act: -0.0000

Data Index: 1435025 (Python Code)

Max Activating Token Index: 621

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1586924 (Python Code)

Max Activating Token Index: 636

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1584809 (Python Code)

Max Activating Token Index: 825

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1393060 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0528. Min Act: -0.0000

Data Index: 1524501 (Python Code)

Max Activating Token Index: 620

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1497318 (Python Code)

Max Activating Token Index: 635

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0493. Min Act: -0.0000

Data Index: 1499929 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1398801 (Python Code)

Max Activating Token Index: 950

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1408909 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1569870 (Python Code)

Max Activating Token Index: 182

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0452. Min Act: -0.0000

Data Index: 1629824 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1502627 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1390612 (Python Code)

Max Activating Token Index: 186