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

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

Neuron 2974 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1490218 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1529891 (Python Code)

Max Activating Token Index: 655

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1526441 (Python Code)

Max Activating Token Index: 597

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1389825 (Python Code)

Max Activating Token Index: 151

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1489731 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1536867 (Python Code)

Max Activating Token Index: 1018

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1533959 (Python Code)

Max Activating Token Index: 459

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1627028 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1490569 (Python Code)

Max Activating Token Index: 421

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1554974 (Python Code)

Max Activating Token Index: 340

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1559479 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1572300 (Python Code)

Max Activating Token Index: 911

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1544536 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1506477 (Python Code)

Max Activating Token Index: 809

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0524. Min Act: -0.0002

Data Index: 1481376 (Python Code)

Max Activating Token Index: 466

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0502. Min Act: -0.0002

Data Index: 1380197 (Python Code)

Max Activating Token Index: 172

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1572390 (Python Code)

Max Activating Token Index: 656

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1566477 (Python Code)

Max Activating Token Index: 663

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1493967 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1474465 (Python Code)

Max Activating Token Index: 39