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

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

Neuron 4482 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1495391 (Python Code)

Max Activating Token Index: 3

Text #1

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1655434 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0272. Min Act: -0.0000

Data Index: 1458396 (Python Code)

Max Activating Token Index: 624

Text #3

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1521337 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1479303 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1617418 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0773. Min Act: -0.0000

Data Index: 1634796 (Python Code)

Max Activating Token Index: 802

Text #7

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0258. Min Act: -0.0000

Data Index: 1498653 (Python Code)

Max Activating Token Index: 16

Text #8

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1401310 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1443661 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1419011 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1612126 (Python Code)

Max Activating Token Index: 517

Text #12

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1509489 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1414016 (Python Code)

Max Activating Token Index: 551

Text #14

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1517819 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1542860 (Python Code)

Max Activating Token Index: 541

Text #16

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1363160 (Python Code)

Max Activating Token Index: 799

Text #17

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1614072 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1556202 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1517568 (Python Code)

Max Activating Token Index: 4