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

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

Neuron 3226 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4793. Min Range: -2.4793

Max Act: 2.3968. Min Act: 0.0000

Data Index: 376839 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 2.4793. Min Range: -2.4793

Max Act: 2.4793. Min Act: -0.0000

Data Index: 1471295 (Python Code)

Max Activating Token Index: 363

Text #2

Max Range: 2.4793. Min Range: -2.4793

Max Act: 2.4730. Min Act: -0.0000

Data Index: 1469919 (Python Code)

Max Activating Token Index: 605

Text #3

Max Range: 2.4793. Min Range: -2.4793

Max Act: 2.2774. Min Act: -0.0000

Data Index: 1226376 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.4793. Min Range: -2.4793

Max Act: 2.2625. Min Act: -0.0000

Data Index: 341455 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.9883. Min Act: -0.0000

Data Index: 153224 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.7246. Min Act: -0.0000

Data Index: 843798 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.9890. Min Act: -0.0000

Data Index: 457919 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.9744. Min Act: -0.0000

Data Index: 1513736 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.7186. Min Act: -0.0000

Data Index: 214425 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.9596. Min Act: -0.0000

Data Index: 1046833 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.8021. Min Act: -0.0000

Data Index: 479054 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.7821. Min Act: -0.0000

Data Index: 426105 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.7485. Min Act: -0.0000

Data Index: 308421 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.8586. Min Act: -0.0000

Data Index: 363738 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.9291. Min Act: -0.0000

Data Index: 1553953 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.7291. Min Act: -0.0000

Data Index: 574851 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.7713. Min Act: -0.0000

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.9640. Min Act: -0.0000

Data Index: 1391320 (Python Code)

Max Activating Token Index: 344

Text #19

Max Range: 2.4793. Min Range: -2.4793

Max Act: 1.8050. Min Act: -0.0000

Data Index: 341640 (C4 (Web Text))

Max Activating Token Index: 939