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

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

Neuron 2896 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1420743 (Python Code)

Max Activating Token Index: 548

Text #1

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.7801. Min Act: -0.0000

Data Index: 1364836 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1548015 (Python Code)

Max Activating Token Index: 896

Text #3

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1563025 (Python Code)

Max Activating Token Index: 892

Text #4

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1394202 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1374930 (Python Code)

Max Activating Token Index: 1020

Text #6

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1454542 (Python Code)

Max Activating Token Index: 849

Text #7

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1517068 (Python Code)

Max Activating Token Index: 814

Text #8

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1582188 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1529328 (Python Code)

Max Activating Token Index: 170

Text #10

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1509272 (Python Code)

Max Activating Token Index: 35

Text #11

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.5903. Min Act: -0.0001

Data Index: 1499218 (Python Code)

Max Activating Token Index: 84

Text #12

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1553664 (Python Code)

Max Activating Token Index: 509

Text #13

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1586622 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1583113 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1506405 (Python Code)

Max Activating Token Index: 225

Text #16

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1512741 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.5671. Min Act: -0.0000

Data Index: 1612491 (Python Code)

Max Activating Token Index: 477

Text #18

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1577486 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 0.8907. Min Range: -0.8907

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1436230 (Python Code)

Max Activating Token Index: 195