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

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

Neuron 2582 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: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1465998 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0718. Min Act: -0.0002

Data Index: 1383330 (Python Code)

Max Activating Token Index: 322

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0718. Min Act: -0.0002

Data Index: 781198 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0717. Min Act: -0.0002

Data Index: 1537034 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1612119 (Python Code)

Max Activating Token Index: 98

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1371593 (Python Code)

Max Activating Token Index: 810

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0661. Min Act: -0.0002

Data Index: 163802 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1496077 (Python Code)

Max Activating Token Index: 432

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1443884 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1562670 (Python Code)

Max Activating Token Index: 679

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1449566 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1565789 (Python Code)

Max Activating Token Index: 482

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1379031 (Python Code)

Max Activating Token Index: 440

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1485144 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1617601 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1444687 (Python Code)

Max Activating Token Index: 826

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1530121 (Python Code)

Max Activating Token Index: 195

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1395890 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1606748 (Python Code)

Max Activating Token Index: 698

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1638782 (Python Code)

Max Activating Token Index: 636