Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2529 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.8977. Min Act: -0.0000

Data Index: 1563261 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 3.0719. Min Range: -3.0719

Max Act: 3.0502. Min Act: -0.0000

Data Index: 1649624 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.9205. Min Act: -0.0000

Data Index: 1577492 (Python Code)

Max Activating Token Index: 280

Text #3

Max Range: 3.0719. Min Range: -3.0719

Max Act: 3.0719. Min Act: -0.0000

Data Index: 1506797 (Python Code)

Max Activating Token Index: 832

Text #4

Max Range: 3.0719. Min Range: -3.0719

Max Act: 3.0345. Min Act: -0.0000

Data Index: 1636223 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.7241. Min Act: -0.0000

Data Index: 1586398 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.6772. Min Act: -0.0000

Data Index: 1400605 (Python Code)

Max Activating Token Index: 310

Text #7

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.6632. Min Act: -0.0000

Data Index: 1623549 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.9030. Min Act: -0.0000

Data Index: 1631512 (Python Code)

Max Activating Token Index: 643

Text #9

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.8772. Min Act: -0.0000

Data Index: 1409539 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.5764. Min Act: -0.0000

Data Index: 1513359 (Python Code)

Max Activating Token Index: 116

Text #11

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.7018. Min Act: -0.0000

Data Index: 1460454 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.7123. Min Act: -0.0000

Data Index: 1603895 (Python Code)

Max Activating Token Index: 892

Text #13

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1394228 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.7191. Min Act: -0.0000

Data Index: 1593570 (Python Code)

Max Activating Token Index: 560

Text #15

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.4378. Min Act: -0.0000

Data Index: 1398340 (Python Code)

Max Activating Token Index: 572

Text #16

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.8351. Min Act: -0.0000

Data Index: 1499369 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.5065. Min Act: -0.0000

Data Index: 1423157 (Python Code)

Max Activating Token Index: 802

Text #18

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.4659. Min Act: -0.0000

Data Index: 1591533 (Python Code)

Max Activating Token Index: 19

Text #19

Max Range: 3.0719. Min Range: -3.0719

Max Act: 2.5872. Min Act: -0.0000

Data Index: 1440579 (Python Code)

Max Activating Token Index: 338