Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 698 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0481. Min Range: -1.0481

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1508306 (Python Code)

Max Activating Token Index: 442

Text #1

Max Range: 1.0481. Min Range: -1.0481

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1550685 (Python Code)

Max Activating Token Index: 594

Text #2

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1624430 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1251361 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8074. Min Act: -0.0000

Data Index: 12164 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1037493 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8249. Min Act: -0.0000

Data Index: 749060 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7959. Min Act: -0.0000

Data Index: 802434 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7865. Min Act: -0.0000

Data Index: 263106 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7615. Min Act: -0.0000

Data Index: 244274 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1362650 (Python Code)

Max Activating Token Index: 445

Text #11

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1233515 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1494874 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7168. Min Act: -0.0000

Data Index: 294226 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7148. Min Act: -0.0000

Data Index: 567718 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1621937 (Python Code)

Max Activating Token Index: 212

Text #16

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1035452 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1054050 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6851. Min Act: -0.0000

Data Index: 132240 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.6662. Min Act: -0.0000

Data Index: 586237 (C4 (Web Text))

Max Activating Token Index: 651