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

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

Neuron 972 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.6847. Min Act: -0.0000

Data Index: 1512565 (Python Code)

Max Activating Token Index: 1014

Text #1

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.4850. Min Act: -0.0000

Data Index: 1526128 (Python Code)

Max Activating Token Index: 395

Text #2

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.3255. Min Act: -0.0000

Data Index: 1585135 (Python Code)

Max Activating Token Index: 454

Text #3

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.2623. Min Act: -0.0000

Data Index: 1428826 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1641270 (Python Code)

Max Activating Token Index: 712

Text #5

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.0732. Min Act: -0.0000

Data Index: 1346050 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.1980. Min Act: -0.0000

Data Index: 1457550 (Python Code)

Max Activating Token Index: 111

Text #7

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.1736. Min Act: -0.0000

Data Index: 1406488 (Python Code)

Max Activating Token Index: 447

Text #8

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.0811. Min Act: -0.0000

Data Index: 1414085 (Python Code)

Max Activating Token Index: 531

Text #9

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.0746. Min Act: -0.0000

Data Index: 1628909 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.1887. Min Act: -0.0000

Data Index: 1549167 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 2.6847. Min Range: -2.6847

Max Act: 1.9744. Min Act: -0.0000

Data Index: 1459351 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 2.6847. Min Range: -2.6847

Max Act: 2.0969. Min Act: -0.0000

Data Index: 1542342 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 2.6847. Min Range: -2.6847

Max Act: 1.8606. Min Act: -0.0000

Data Index: 1615002 (Python Code)

Max Activating Token Index: 34

Text #14

Max Range: 2.6847. Min Range: -2.6847

Max Act: 1.9029. Min Act: -0.0000

Data Index: 1465409 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 2.6847. Min Range: -2.6847

Max Act: 1.8829. Min Act: -0.0000

Data Index: 1628102 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 2.6847. Min Range: -2.6847

Max Act: 1.9920. Min Act: -0.0000

Data Index: 1617593 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 2.6847. Min Range: -2.6847

Max Act: 1.7182. Min Act: -0.0000

Data Index: 1534439 (Python Code)

Max Activating Token Index: 199

Text #18

Max Range: 2.6847. Min Range: -2.6847

Max Act: 1.8176. Min Act: -0.0000

Data Index: 1654636 (Python Code)

Max Activating Token Index: 558

Text #19

Max Range: 2.6847. Min Range: -2.6847

Max Act: 1.8054. Min Act: -0.0000

Data Index: 1626621 (Python Code)

Max Activating Token Index: 383