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

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

Neuron 4774 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2150. Min Act: -0.0003

Data Index: 74853 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2120. Min Act: -0.0003

Data Index: 112921 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2020. Min Act: -0.0002

Data Index: 258198 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2075. Min Act: -0.0003

Data Index: 998668 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2072. Min Act: -0.0003

Data Index: 736375 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2019. Min Act: -0.0003

Data Index: 1234427 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2017. Min Act: -0.0003

Data Index: 544148 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2088. Min Act: -0.0003

Data Index: 522005 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1992. Min Act: -0.0003

Data Index: 2300 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1977. Min Act: -0.0003

Data Index: 557120 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.2012. Min Act: -0.0003

Data Index: 788209 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1997. Min Act: -0.0003

Data Index: 438744 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1936. Min Act: -0.0003

Data Index: 354075 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1925. Min Act: -0.0003

Data Index: 1074225 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1851. Min Act: -0.0003

Data Index: 458087 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1907. Min Act: -0.0003

Data Index: 1111375 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1889. Min Act: -0.0003

Data Index: 74425 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1897. Min Act: -0.0003

Data Index: 1210482 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1874. Min Act: -0.0003

Data Index: 237282 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.2150. Min Range: -0.2150

Max Act: 0.1939. Min Act: -0.0003

Data Index: 1270484 (C4 (Web Text))

Max Activating Token Index: 673