Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 196 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0665. Min Act: -0.0006

Data Index: 1383023 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0006

Data Index: 1415286 (Python Code)

Max Activating Token Index: 523

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0688. Min Act: -0.0006

Data Index: 1437413 (Python Code)

Max Activating Token Index: 445

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0597. Min Act: -0.0006

Data Index: 1540124 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0627. Min Act: -0.0006

Data Index: 1387924 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0651. Min Act: -0.0006

Data Index: 1554138 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0635. Min Act: -0.0006

Data Index: 1510635 (Python Code)

Max Activating Token Index: 577

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0648. Min Act: -0.0006

Data Index: 1371047 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0614. Min Act: -0.0006

Data Index: 1643412 (Python Code)

Max Activating Token Index: 772

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0609. Min Act: -0.0006

Data Index: 1630314 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0613. Min Act: -0.0006

Data Index: 1633070 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0577. Min Act: -0.0006

Data Index: 1539970 (Python Code)

Max Activating Token Index: 584

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0609. Min Act: -0.0006

Data Index: 1560577 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0609. Min Act: -0.0006

Data Index: 1432667 (Python Code)

Max Activating Token Index: 404

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0638. Min Act: -0.0006

Data Index: 1465913 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0616. Min Act: -0.0006

Data Index: 1374470 (Python Code)

Max Activating Token Index: 490

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0601. Min Act: -0.0006

Data Index: 1603419 (Python Code)

Max Activating Token Index: 391

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0614. Min Act: -0.0006

Data Index: 1367865 (Python Code)

Max Activating Token Index: 648

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0587. Min Act: -0.0006

Data Index: 1496351 (Python Code)

Max Activating Token Index: 223

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0585. Min Act: -0.0006

Data Index: 1544501 (Python Code)

Max Activating Token Index: 576