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

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

Neuron 192 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.9794. Min Act: -0.0001

Data Index: 1480564 (Python Code)

Max Activating Token Index: 786

Text #1

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.3228. Min Act: -0.0001

Data Index: 1442678 (Python Code)

Max Activating Token Index: 333

Text #2

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.4225. Min Act: -0.0001

Data Index: 1455765 (Python Code)

Max Activating Token Index: 593

Text #3

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.9999. Min Act: -0.0001

Data Index: 1644159 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.4779. Min Act: -0.0001

Data Index: 1606379 (Python Code)

Max Activating Token Index: 455

Text #5

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.6463. Min Act: -0.0001

Data Index: 1567158 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.6430. Min Act: -0.0001

Data Index: 1459641 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.3229. Min Act: -0.0001

Data Index: 1542046 (Python Code)

Max Activating Token Index: 638

Text #8

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.6545. Min Act: -0.0001

Data Index: 1406597 (Python Code)

Max Activating Token Index: 776

Text #9

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.1127. Min Act: -0.0001

Data Index: 1436847 (Python Code)

Max Activating Token Index: 263

Text #10

Max Range: 5.9999. Min Range: -5.9999

Max Act: 4.9471. Min Act: -0.0001

Data Index: 1647077 (Python Code)

Max Activating Token Index: 392

Text #11

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.0793. Min Act: -0.0001

Data Index: 1421058 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 5.9999. Min Range: -5.9999

Max Act: 4.8988. Min Act: -0.0001

Data Index: 1474836 (Python Code)

Max Activating Token Index: 349

Text #13

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.2325. Min Act: -0.0001

Data Index: 1573577 (Python Code)

Max Activating Token Index: 308

Text #14

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.7262. Min Act: -0.0001

Data Index: 1578894 (Python Code)

Max Activating Token Index: 405

Text #15

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.3671. Min Act: -0.0001

Data Index: 1628413 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 5.9999. Min Range: -5.9999

Max Act: 5.1968. Min Act: -0.0001

Data Index: 1376488 (Python Code)

Max Activating Token Index: 664

Text #17

Max Range: 5.9999. Min Range: -5.9999

Max Act: 4.6539. Min Act: -0.0001

Data Index: 1478757 (Python Code)

Max Activating Token Index: 337

Text #18

Max Range: 5.9999. Min Range: -5.9999

Max Act: 4.8058. Min Act: -0.0001

Data Index: 1503507 (Python Code)

Max Activating Token Index: 243

Text #19

Max Range: 5.9999. Min Range: -5.9999

Max Act: 4.9741. Min Act: -0.0001

Data Index: 1490553 (Python Code)

Max Activating Token Index: 376