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

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

Neuron 2359 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: 2.2872. Min Range: -2.2872

Max Act: 2.2872. Min Act: 0.0000

Data Index: 1539716 (Python Code)

Max Activating Token Index: 802

Text #1

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.1689. Min Act: -0.0000

Data Index: 1554207 (Python Code)

Max Activating Token Index: 969

Text #2

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.1661. Min Act: -0.0000

Data Index: 1542507 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.2815. Min Act: -0.0000

Data Index: 1583324 (Python Code)

Max Activating Token Index: 233

Text #4

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.0513. Min Act: -0.0000

Data Index: 1376121 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.0265. Min Act: -0.0000

Data Index: 1597469 (Python Code)

Max Activating Token Index: 255

Text #6

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.2320. Min Act: 0.0000

Data Index: 1441200 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.2012. Min Act: -0.0000

Data Index: 1648305 (Python Code)

Max Activating Token Index: 676

Text #8

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.0879. Min Act: -0.0000

Data Index: 1430643 (Python Code)

Max Activating Token Index: 854

Text #9

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.1993. Min Act: -0.0000

Data Index: 1499147 (Python Code)

Max Activating Token Index: 1019

Text #10

Max Range: 2.2872. Min Range: -2.2872

Max Act: 1.9977. Min Act: -0.0000

Data Index: 1542870 (Python Code)

Max Activating Token Index: 190

Text #11

Max Range: 2.2872. Min Range: -2.2872

Max Act: 1.9664. Min Act: -0.0000

Data Index: 1536117 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.0745. Min Act: -0.0000

Data Index: 1646084 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 2.2872. Min Range: -2.2872

Max Act: 1.9563. Min Act: 0.0000

Data Index: 1497348 (Python Code)

Max Activating Token Index: 641

Text #14

Max Range: 2.2872. Min Range: -2.2872

Max Act: 1.9452. Min Act: -0.0000

Data Index: 1553722 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 2.2872. Min Range: -2.2872

Max Act: 1.9364. Min Act: -0.0000

Data Index: 1391715 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 2.2872. Min Range: -2.2872

Max Act: 1.9309. Min Act: -0.0000

Data Index: 1386443 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 2.2872. Min Range: -2.2872

Max Act: 1.9202. Min Act: -0.0000

Data Index: 1600132 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 2.2872. Min Range: -2.2872

Max Act: 2.0133. Min Act: -0.0000

Data Index: 1501490 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 2.2872. Min Range: -2.2872

Max Act: 1.9084. Min Act: 0.0000

Data Index: 1541065 (Python Code)

Max Activating Token Index: 234