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

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

Neuron 880 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: 0.1099. Min Range: -0.1099

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1433704 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1543774 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1582277 (Python Code)

Max Activating Token Index: 269

Text #3

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1472359 (Python Code)

Max Activating Token Index: 699

Text #4

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1631566 (Python Code)

Max Activating Token Index: 285

Text #5

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1430775 (Python Code)

Max Activating Token Index: 975

Text #6

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1542839 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1485649 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1384508 (Python Code)

Max Activating Token Index: 631

Text #9

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1453784 (Python Code)

Max Activating Token Index: 103

Text #10

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1427075 (Python Code)

Max Activating Token Index: 1021

Text #11

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1582352 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1635385 (Python Code)

Max Activating Token Index: 588

Text #13

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1365493 (Python Code)

Max Activating Token Index: 634

Text #14

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1502244 (Python Code)

Max Activating Token Index: 926

Text #15

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1421987 (Python Code)

Max Activating Token Index: 410

Text #16

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1495096 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1607799 (Python Code)

Max Activating Token Index: 354

Text #18

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1462302 (Python Code)

Max Activating Token Index: 476

Text #19

Max Range: 0.1099. Min Range: -0.1099

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1362011 (Python Code)

Max Activating Token Index: 943