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

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

Neuron 3412 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1449754 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5619. Min Act: -0.0000

Data Index: 477631 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1363111 (Python Code)

Max Activating Token Index: 810

Text #3

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1363927 (Python Code)

Max Activating Token Index: 404

Text #4

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5260. Min Act: -0.0000

Data Index: 463869 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1446584 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5696. Min Act: -0.0000

Data Index: 584848 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1012500 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1378554 (Python Code)

Max Activating Token Index: 263

Text #9

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1617392 (Python Code)

Max Activating Token Index: 818

Text #10

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1403863 (Python Code)

Max Activating Token Index: 648

Text #11

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1481234 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1515558 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4750. Min Act: -0.0000

Data Index: 480321 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1653521 (Python Code)

Max Activating Token Index: 397

Text #15

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1638186 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4489. Min Act: -0.0000

Data Index: 785818 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1482355 (Python Code)

Max Activating Token Index: 552

Text #18

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1404148 (Python Code)

Max Activating Token Index: 828

Text #19

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1171959 (C4 (Web Text))

Max Activating Token Index: 806