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

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

Neuron 5082 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: 0.9787. Min Range: -0.9787

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1567354 (Python Code)

Max Activating Token Index: 892

Text #1

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1549066 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9337. Min Act: -0.0000

Data Index: 1621335 (Python Code)

Max Activating Token Index: 584

Text #3

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1638741 (Python Code)

Max Activating Token Index: 603

Text #4

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1631151 (Python Code)

Max Activating Token Index: 88

Text #5

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1413980 (Python Code)

Max Activating Token Index: 694

Text #6

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1362161 (Python Code)

Max Activating Token Index: 415

Text #7

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1560803 (Python Code)

Max Activating Token Index: 261

Text #8

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1652524 (Python Code)

Max Activating Token Index: 558

Text #9

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1560972 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1373702 (Python Code)

Max Activating Token Index: 824

Text #11

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1577481 (Python Code)

Max Activating Token Index: 166

Text #12

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1385328 (Python Code)

Max Activating Token Index: 355

Text #13

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1490916 (Python Code)

Max Activating Token Index: 594

Text #14

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1491755 (Python Code)

Max Activating Token Index: 783

Text #15

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1608362 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1467588 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1574722 (Python Code)

Max Activating Token Index: 879

Text #18

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1642004 (Python Code)

Max Activating Token Index: 811

Text #19

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1591608 (Python Code)

Max Activating Token Index: 103