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

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

Neuron 3219 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0480. Min Range: -1.0480

Max Act: 1.0480. Min Act: -0.0001

Data Index: 304321 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9643. Min Act: -0.0001

Data Index: 1380599 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8011. Min Act: -0.0001

Data Index: 144338 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9732. Min Act: -0.0001

Data Index: 1488743 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.9310. Min Act: -0.0001

Data Index: 1379865 (Python Code)

Max Activating Token Index: 572

Text #5

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8290. Min Act: -0.0001

Data Index: 13452 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8729. Min Act: -0.0001

Data Index: 247302 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8714. Min Act: -0.0001

Data Index: 1527073 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8140. Min Act: -0.0001

Data Index: 1219515 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8366. Min Act: -0.0001

Data Index: 456197 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7899. Min Act: -0.0001

Data Index: 1420041 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.7597. Min Act: -0.0001

Data Index: 1430142 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8724. Min Act: -0.0001

Data Index: 1382611 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8754. Min Act: -0.0001

Data Index: 1416227 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1612856 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8885. Min Act: -0.0001

Data Index: 1534226 (Python Code)

Max Activating Token Index: 25

Text #16

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8260. Min Act: -0.0001

Data Index: 1480813 (Python Code)

Max Activating Token Index: 786

Text #17

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8465. Min Act: -0.0001

Data Index: 1490957 (Python Code)

Max Activating Token Index: 124

Text #18

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8273. Min Act: -0.0001

Data Index: 1438405 (Python Code)

Max Activating Token Index: 145

Text #19

Max Range: 1.0480. Min Range: -1.0480

Max Act: 0.8139. Min Act: -0.0001

Data Index: 1593874 (Python Code)

Max Activating Token Index: 90