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

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

Neuron 590 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1569734 (Python Code)

Max Activating Token Index: 709

Text #1

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1595317 (Python Code)

Max Activating Token Index: 557

Text #2

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1539120 (Python Code)

Max Activating Token Index: 971

Text #3

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1326266 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0599. Min Act: -0.0000

Data Index: 279885 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0619. Min Act: -0.0000

Data Index: 1464306 (Python Code)

Max Activating Token Index: 570

Text #6

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0620. Min Act: -0.0000

Data Index: 553648 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0604. Min Act: -0.0000

Data Index: 446149 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0594. Min Act: -0.0000

Data Index: 426088 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0584. Min Act: -0.0000

Data Index: 109254 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0539. Min Act: -0.0000

Data Index: 464844 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0577. Min Act: -0.0000

Data Index: 1302422 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0569. Min Act: -0.0000

Data Index: 429412 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0546. Min Act: -0.0000

Data Index: 1499564 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1037354 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1534972 (Python Code)

Max Activating Token Index: 321

Text #16

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1437722 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1167565 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0514. Min Act: -0.0000

Data Index: 433568 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0540. Min Act: -0.0000

Data Index: 46181 (C4 (Web Text))

Max Activating Token Index: 986