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

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

Neuron 845 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: 3.3849. Min Range: -3.3849

Max Act: 3.3849. Min Act: -0.0000

Data Index: 1615736 (Python Code)

Max Activating Token Index: 63

Text #1

Max Range: 3.3849. Min Range: -3.3849

Max Act: 3.2474. Min Act: -0.0000

Data Index: 1586022 (Python Code)

Max Activating Token Index: 432

Text #2

Max Range: 3.3849. Min Range: -3.3849

Max Act: 2.7381. Min Act: -0.0000

Data Index: 1608980 (Python Code)

Max Activating Token Index: 556

Text #3

Max Range: 3.3849. Min Range: -3.3849

Max Act: 2.6306. Min Act: -0.0000

Data Index: 1480731 (Python Code)

Max Activating Token Index: 773

Text #4

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.7821. Min Act: -0.0000

Data Index: 1418567 (Python Code)

Max Activating Token Index: 942

Text #5

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.7598. Min Act: -0.0000

Data Index: 1405163 (Python Code)

Max Activating Token Index: 385

Text #6

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.6556. Min Act: -0.0000

Data Index: 876058 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.6472. Min Act: -0.0000

Data Index: 1565117 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.5710. Min Act: -0.0000

Data Index: 590603 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.5218. Min Act: -0.0000

Data Index: 1629976 (Python Code)

Max Activating Token Index: 956

Text #10

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.6445. Min Act: -0.0000

Data Index: 123298 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.6201. Min Act: -0.0000

Data Index: 1644833 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.5891. Min Act: -0.0000

Data Index: 908647 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.6104. Min Act: -0.0000

Data Index: 638105 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.6054. Min Act: -0.0000

Data Index: 1558244 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.5445. Min Act: -0.0000

Data Index: 219374 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.5832. Min Act: -0.0000

Data Index: 605263 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.5724. Min Act: -0.0000

Data Index: 454303 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1603785 (Python Code)

Max Activating Token Index: 546

Text #19

Max Range: 3.3849. Min Range: -3.3849

Max Act: 1.5786. Min Act: -0.0000

Data Index: 1654019 (Python Code)

Max Activating Token Index: 554