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

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

Neuron 2976 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.7586. Min Act: -0.0000

Data Index: 480795 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.6321. Min Act: -0.0000

Data Index: 1578635 (Python Code)

Max Activating Token Index: 89

Text #2

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1636032 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1598836 (Python Code)

Max Activating Token Index: 472

Text #4

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.3597. Min Act: -0.0000

Data Index: 1365232 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.2536. Min Act: -0.0000

Data Index: 877278 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1382711 (Python Code)

Max Activating Token Index: 809

Text #7

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1405207 (Python Code)

Max Activating Token Index: 659

Text #8

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.2009. Min Act: -0.0000

Data Index: 1123575 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.2520. Min Act: -0.0000

Data Index: 259257 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.1705. Min Act: -0.0000

Data Index: 1394246 (Python Code)

Max Activating Token Index: 141

Text #11

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.0959. Min Act: -0.0000

Data Index: 1483872 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1638429 (Python Code)

Max Activating Token Index: 418

Text #13

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1401786 (Python Code)

Max Activating Token Index: 409

Text #14

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1176367 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1508792 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.1454. Min Act: -0.0000

Data Index: 706520 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.0640. Min Act: -0.0000

Data Index: 1400606 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 1.7586. Min Range: -1.7586

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1652332 (Python Code)

Max Activating Token Index: 442

Text #19

Max Range: 1.7586. Min Range: -1.7586

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1420242 (Python Code)

Max Activating Token Index: 496