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

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

Neuron 1056 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.6242. Min Act: -0.0000

Data Index: 1525153 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1559519 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1385344 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1404955 (Python Code)

Max Activating Token Index: 644

Text #4

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1514226 (Python Code)

Max Activating Token Index: 335

Text #5

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1400223 (Python Code)

Max Activating Token Index: 223

Text #6

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1506861 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1565979 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1495023 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5814. Min Act: 0.0000

Data Index: 1410771 (Python Code)

Max Activating Token Index: 462

Text #10

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1651081 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1487774 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5180. Min Act: -0.0000

Data Index: 204520 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1541634 (Python Code)

Max Activating Token Index: 225

Text #14

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1566964 (Python Code)

Max Activating Token Index: 296

Text #15

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1629586 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1655511 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1580918 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1516612 (Python Code)

Max Activating Token Index: 779

Text #19

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1616985 (Python Code)

Max Activating Token Index: 109