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

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

Neuron 3423 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: 0.0958. Min Range: -0.0958

Max Act: 0.0958. Min Act: -0.0002

Data Index: 921337 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1501222 (Python Code)

Max Activating Token Index: 382

Text #2

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1363134 (Python Code)

Max Activating Token Index: 64

Text #3

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0700. Min Act: -0.0002

Data Index: 323799 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1470581 (Python Code)

Max Activating Token Index: 508

Text #5

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1593787 (Python Code)

Max Activating Token Index: 354

Text #6

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0642. Min Act: -0.0002

Data Index: 387060 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1383341 (Python Code)

Max Activating Token Index: 370

Text #8

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1367801 (Python Code)

Max Activating Token Index: 792

Text #9

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1536375 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1455645 (Python Code)

Max Activating Token Index: 42

Text #11

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1483627 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0638. Min Act: -0.0002

Data Index: 439763 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0614. Min Act: -0.0002

Data Index: 214454 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1442505 (Python Code)

Max Activating Token Index: 496

Text #15

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1364406 (Python Code)

Max Activating Token Index: 165

Text #16

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1656642 (Python Code)

Max Activating Token Index: 322

Text #17

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1444654 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1545411 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1549067 (Python Code)

Max Activating Token Index: 121