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

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

Neuron 5801 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.2690. Min Act: -0.0000

Data Index: 1651135 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.1692. Min Act: -0.0000

Data Index: 1509383 (Python Code)

Max Activating Token Index: 846

Text #2

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1452027 (Python Code)

Max Activating Token Index: 892

Text #3

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1633800 (Python Code)

Max Activating Token Index: 436

Text #4

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1580227 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.0466. Min Act: -0.0000

Data Index: 1600576 (Python Code)

Max Activating Token Index: 817

Text #6

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1533757 (Python Code)

Max Activating Token Index: 682

Text #7

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1549139 (Python Code)

Max Activating Token Index: 499

Text #8

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.0021. Min Act: -0.0000

Data Index: 1373990 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9820. Min Act: -0.0000

Data Index: 1602628 (Python Code)

Max Activating Token Index: 572

Text #10

Max Range: 1.2690. Min Range: -1.2690

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1596819 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1517670 (Python Code)

Max Activating Token Index: 664

Text #12

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1525757 (Python Code)

Max Activating Token Index: 891

Text #13

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1360462 (Python Code)

Max Activating Token Index: 794

Text #14

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1614634 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8743. Min Act: -0.0000

Data Index: 537611 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1578753 (Python Code)

Max Activating Token Index: 613

Text #17

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8879. Min Act: -0.0000

Data Index: 635859 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1603817 (Python Code)

Max Activating Token Index: 623

Text #19

Max Range: 1.2690. Min Range: -1.2690

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1527069 (Python Code)

Max Activating Token Index: 127