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

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

Neuron 697 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1168608 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1646218 (Python Code)

Max Activating Token Index: 206

Text #2

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1601250 (Python Code)

Max Activating Token Index: 475

Text #3

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1470808 (Python Code)

Max Activating Token Index: 837

Text #4

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1619046 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1362798 (Python Code)

Max Activating Token Index: 253

Text #6

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1570498 (Python Code)

Max Activating Token Index: 164

Text #7

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1423055 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1540708 (Python Code)

Max Activating Token Index: 395

Text #9

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1415216 (Python Code)

Max Activating Token Index: 272

Text #10

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1597055 (Python Code)

Max Activating Token Index: 137

Text #11

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1372146 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1630581 (Python Code)

Max Activating Token Index: 275

Text #13

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1563177 (Python Code)

Max Activating Token Index: 261

Text #14

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1651734 (Python Code)

Max Activating Token Index: 700

Text #15

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1470601 (Python Code)

Max Activating Token Index: 817

Text #16

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1585957 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1461369 (Python Code)

Max Activating Token Index: 751

Text #18

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1598876 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.1000. Min Range: -0.1000

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1487963 (Python Code)

Max Activating Token Index: 273