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

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

Neuron 3240 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.3651. Min Act: -0.0000

Data Index: 745651 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1895. Min Act: -0.0000

Data Index: 791895 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1916. Min Act: -0.0000

Data Index: 672716 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1795. Min Act: -0.0000

Data Index: 596888 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1307730 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1679. Min Act: -0.0000

Data Index: 40456 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1695. Min Act: -0.0000

Data Index: 158328 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1702. Min Act: -0.0000

Data Index: 809923 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1619. Min Act: -0.0001

Data Index: 551185 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1753. Min Act: -0.0000

Data Index: 5946 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1603. Min Act: -0.0000

Data Index: 293755 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1506. Min Act: -0.0000

Data Index: 223384 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1020893 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1572. Min Act: -0.0000

Data Index: 912210 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1336209 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1622. Min Act: -0.0000

Data Index: 474905 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1143679 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1262655 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1594. Min Act: -0.0000

Data Index: 587589 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.3651. Min Range: -0.3651

Max Act: 0.1484. Min Act: -0.0001

Data Index: 515401 (C4 (Web Text))

Max Activating Token Index: 249