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

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

Neuron 3327 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3574. Min Range: -1.3574

Max Act: 1.3574. Min Act: -0.0000

Data Index: 304026 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.3574. Min Range: -1.3574

Max Act: 1.1937. Min Act: -0.0000

Data Index: 49556 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 1.3574. Min Range: -1.3574

Max Act: 1.0570. Min Act: -0.0000

Data Index: 224741 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 1.3574. Min Range: -1.3574

Max Act: 1.0328. Min Act: -0.0000

Data Index: 392909 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 1.3574. Min Range: -1.3574

Max Act: 1.0153. Min Act: 0.0000

Data Index: 1553341 (Python Code)

Max Activating Token Index: 959

Text #5

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.9615. Min Act: 0.0000

Data Index: 1377518 (Python Code)

Max Activating Token Index: 825

Text #6

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.9128. Min Act: 0.0000

Data Index: 1398477 (Python Code)

Max Activating Token Index: 475

Text #7

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.9102. Min Act: -0.0000

Data Index: 165595 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.8836. Min Act: -0.0000

Data Index: 48174 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.8579. Min Act: 0.0000

Data Index: 1373360 (Python Code)

Max Activating Token Index: 547

Text #10

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.9501. Min Act: -0.0000

Data Index: 646911 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.8214. Min Act: 0.0000

Data Index: 1409173 (Python Code)

Max Activating Token Index: 941

Text #12

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.9122. Min Act: -0.0000

Data Index: 534017 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.8529. Min Act: -0.0000

Data Index: 270011 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.8242. Min Act: 0.0000

Data Index: 1514163 (Python Code)

Max Activating Token Index: 917

Text #15

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.7735. Min Act: -0.0000

Data Index: 821803 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.7668. Min Act: 0.0000

Data Index: 1422797 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1179188 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.8030. Min Act: 0.0000

Data Index: 1445148 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 1.3574. Min Range: -1.3574

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1036738 (C4 (Web Text))

Max Activating Token Index: 993