Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2886 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.2113. Min Act: -0.0001

Data Index: 1360516 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1602532 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1565835 (Python Code)

Max Activating Token Index: 665

Text #3

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.2014. Min Act: -0.0001

Data Index: 1364399 (Python Code)

Max Activating Token Index: 448

Text #4

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1638473 (Python Code)

Max Activating Token Index: 276

Text #5

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1627495 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1543207 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1985. Min Act: -0.0001

Data Index: 1643229 (Python Code)

Max Activating Token Index: 372

Text #8

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1634638 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1566883 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1585410 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1640232 (Python Code)

Max Activating Token Index: 717

Text #12

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1619957 (Python Code)

Max Activating Token Index: 131

Text #13

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1605023 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1705. Min Act: -0.0001

Data Index: 1569811 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1371130 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1669. Min Act: -0.0001

Data Index: 1560715 (Python Code)

Max Activating Token Index: 901

Text #17

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1548197 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1538283 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 0.2125. Min Range: -0.2125

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1569486 (Python Code)

Max Activating Token Index: 281