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

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

Neuron 4693 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: 0.6731. Min Range: -0.6731

Max Act: 0.6731. Min Act: -0.0000

Data Index: 1403119 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1585920 (Python Code)

Max Activating Token Index: 573

Text #2

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1380791 (Python Code)

Max Activating Token Index: 592

Text #3

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1521929 (Python Code)

Max Activating Token Index: 814

Text #4

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1623555 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1455993 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1409196 (Python Code)

Max Activating Token Index: 438

Text #7

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1559195 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1472190 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1445110 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1595364 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1414454 (Python Code)

Max Activating Token Index: 1018

Text #12

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1477923 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1433626 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1623078 (Python Code)

Max Activating Token Index: 824

Text #15

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1470145 (Python Code)

Max Activating Token Index: 19

Text #16

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1590358 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1362670 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1614251 (Python Code)

Max Activating Token Index: 914

Text #19

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1440978 (Python Code)

Max Activating Token Index: 664