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

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

Neuron 2503 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4087. Min Range: -2.4087

Max Act: 2.4087. Min Act: -0.0000

Data Index: 1621581 (Python Code)

Max Activating Token Index: 812

Text #1

Max Range: 2.4087. Min Range: -2.4087

Max Act: 2.0353. Min Act: -0.0000

Data Index: 1437641 (Python Code)

Max Activating Token Index: 424

Text #2

Max Range: 2.4087. Min Range: -2.4087

Max Act: 2.0893. Min Act: -0.0000

Data Index: 1544346 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 2.4087. Min Range: -2.4087

Max Act: 2.1714. Min Act: -0.0000

Data Index: 1459491 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.9978. Min Act: -0.0000

Data Index: 1512523 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 2.4087. Min Range: -2.4087

Max Act: 2.0487. Min Act: -0.0000

Data Index: 1405815 (Python Code)

Max Activating Token Index: 134

Text #6

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.7933. Min Act: -0.0000

Data Index: 1622975 (Python Code)

Max Activating Token Index: 203

Text #7

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8816. Min Act: -0.0000

Data Index: 1366594 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8736. Min Act: -0.0000

Data Index: 1425158 (Python Code)

Max Activating Token Index: 789

Text #9

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8695. Min Act: -0.0000

Data Index: 1605143 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8568. Min Act: -0.0000

Data Index: 1527626 (Python Code)

Max Activating Token Index: 952

Text #11

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8586. Min Act: -0.0000

Data Index: 1600838 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.7990. Min Act: -0.0000

Data Index: 1391840 (Python Code)

Max Activating Token Index: 507

Text #13

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1557117 (Python Code)

Max Activating Token Index: 717

Text #14

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1489635 (Python Code)

Max Activating Token Index: 817

Text #15

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.9405. Min Act: -0.0000

Data Index: 1428816 (Python Code)

Max Activating Token Index: 658

Text #16

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8231. Min Act: -0.0000

Data Index: 1618765 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.8094. Min Act: -0.0000

Data Index: 1372973 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.9120. Min Act: -0.0000

Data Index: 1611741 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 2.4087. Min Range: -2.4087

Max Act: 1.9230. Min Act: -0.0000

Data Index: 1615214 (Python Code)

Max Activating Token Index: 94