Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2831 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1138198 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1337381 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2232. Min Act: -0.0000

Data Index: 45458 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1131580 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1923. Min Act: -0.0001

Data Index: 43781 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1964. Min Act: -0.0001

Data Index: 1287458 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1909. Min Act: -0.0000

Data Index: 918717 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2019. Min Act: -0.0001

Data Index: 523728 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1999. Min Act: -0.0000

Data Index: 230964 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1935. Min Act: -0.0000

Data Index: 147428 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1918. Min Act: -0.0000

Data Index: 602853 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1857. Min Act: -0.0001

Data Index: 850783 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1773. Min Act: -0.0000

Data Index: 523894 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1981. Min Act: -0.0001

Data Index: 206142 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1328840 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1173577 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1824. Min Act: -0.0000

Data Index: 182679 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1675. Min Act: -0.0001

Data Index: 796841 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1725. Min Act: -0.0001

Data Index: 713694 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1777. Min Act: -0.0000

Data Index: 864935 (C4 (Web Text))

Max Activating Token Index: 327