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

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

Neuron 4549 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2497. Min Act: -0.0000

Data Index: 1296828 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2210. Min Act: -0.0000

Data Index: 874687 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1203920 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1079066 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1915. Min Act: -0.0000

Data Index: 698327 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1234086 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.2047. Min Act: -0.0000

Data Index: 848581 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1766. Min Act: -0.0000

Data Index: 410018 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1971. Min Act: -0.0000

Data Index: 934697 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1828. Min Act: -0.0000

Data Index: 888638 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1683. Min Act: -0.0000

Data Index: 706896 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1259897 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1978. Min Act: -0.0000

Data Index: 481739 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1967. Min Act: -0.0000

Data Index: 968734 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1744. Min Act: -0.0000

Data Index: 80945 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1850. Min Act: -0.0000

Data Index: 980627 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1859. Min Act: -0.0000

Data Index: 954718 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1227924 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1667. Min Act: -0.0000

Data Index: 788166 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.2497. Min Range: -0.2497

Max Act: 0.1803. Min Act: -0.0000

Data Index: 158630 (C4 (Web Text))

Max Activating Token Index: 37