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

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

Neuron 760 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: 0.7851. Min Range: -0.7851

Max Act: 0.7851. Min Act: -0.0002

Data Index: 1574114 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6924. Min Act: -0.0002

Data Index: 1466575 (Python Code)

Max Activating Token Index: 763

Text #2

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6209. Min Act: -0.0002

Data Index: 1553205 (Python Code)

Max Activating Token Index: 808

Text #3

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6825. Min Act: -0.0002

Data Index: 1416767 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7674. Min Act: -0.0002

Data Index: 1420466 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6931. Min Act: -0.0002

Data Index: 1391556 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7137. Min Act: -0.0002

Data Index: 1443857 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6820. Min Act: -0.0002

Data Index: 1588189 (Python Code)

Max Activating Token Index: 93

Text #8

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6654. Min Act: -0.0002

Data Index: 1558571 (Python Code)

Max Activating Token Index: 410

Text #9

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6782. Min Act: -0.0002

Data Index: 1597750 (Python Code)

Max Activating Token Index: 519

Text #10

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.7289. Min Act: -0.0002

Data Index: 1386400 (Python Code)

Max Activating Token Index: 275

Text #11

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6112. Min Act: -0.0002

Data Index: 1437495 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6069. Min Act: -0.0002

Data Index: 1415275 (Python Code)

Max Activating Token Index: 835

Text #13

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6690. Min Act: -0.0002

Data Index: 1513721 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5945. Min Act: -0.0002

Data Index: 1397573 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6437. Min Act: -0.0002

Data Index: 1495538 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6119. Min Act: -0.0002

Data Index: 1525726 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6251. Min Act: -0.0002

Data Index: 1504192 (Python Code)

Max Activating Token Index: 892

Text #18

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.6546. Min Act: -0.0002

Data Index: 1558603 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 0.7851. Min Range: -0.7851

Max Act: 0.5759. Min Act: -0.0002

Data Index: 1385643 (Python Code)

Max Activating Token Index: 224