Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2223 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1428221 (Python Code)

Max Activating Token Index: 992

Text #1

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1484746 (Python Code)

Max Activating Token Index: 632

Text #2

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1470186 (Python Code)

Max Activating Token Index: 166

Text #3

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1610133 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1434632 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1473521 (Python Code)

Max Activating Token Index: 310

Text #6

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1488803 (Python Code)

Max Activating Token Index: 357

Text #7

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1450421 (Python Code)

Max Activating Token Index: 731

Text #8

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1536832 (Python Code)

Max Activating Token Index: 142

Text #9

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1414237 (Python Code)

Max Activating Token Index: 496

Text #10

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1582717 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1529988 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1577135 (Python Code)

Max Activating Token Index: 722

Text #13

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1554513 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1479122 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1418118 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1593242 (Python Code)

Max Activating Token Index: 581

Text #17

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1439517 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1567978 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1630838 (Python Code)

Max Activating Token Index: 634