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

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

Neuron 3549 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.8851. Min Act: -0.0001

Data Index: 1467673 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.7749. Min Act: -0.0001

Data Index: 1431534 (Python Code)

Max Activating Token Index: 78

Text #2

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.7992. Min Act: -0.0001

Data Index: 1529838 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.8119. Min Act: -0.0001

Data Index: 1386511 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.7233. Min Act: -0.0001

Data Index: 1616131 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.8770. Min Act: -0.0001

Data Index: 1518194 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6806. Min Act: -0.0001

Data Index: 1526348 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1564843 (Python Code)

Max Activating Token Index: 97

Text #8

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1647076 (Python Code)

Max Activating Token Index: 133

Text #9

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.7472. Min Act: -0.0001

Data Index: 1373903 (Python Code)

Max Activating Token Index: 145

Text #10

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6680. Min Act: -0.0001

Data Index: 1611749 (Python Code)

Max Activating Token Index: 334

Text #11

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6865. Min Act: -0.0001

Data Index: 1378011 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6532. Min Act: -0.0001

Data Index: 1528514 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.7416. Min Act: -0.0001

Data Index: 1613279 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1503423 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6357. Min Act: -0.0001

Data Index: 1568863 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1374925 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.5745. Min Act: -0.0001

Data Index: 1557774 (Python Code)

Max Activating Token Index: 214

Text #18

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6757. Min Act: -0.0001

Data Index: 1561133 (Python Code)

Max Activating Token Index: 607

Text #19

Max Range: 0.8851. Min Range: -0.8851

Max Act: 0.6799. Min Act: -0.0001

Data Index: 1424226 (Python Code)

Max Activating Token Index: 711