Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.8539. Min Act: -0.0000

Data Index: 675465 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.8266. Min Act: -0.0000

Data Index: 746357 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7809. Min Act: -0.0000

Data Index: 202746 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7490. Min Act: -0.0000

Data Index: 1071786 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7430. Min Act: -0.0000

Data Index: 891011 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7867. Min Act: -0.0000

Data Index: 707565 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.7183. Min Act: -0.0000

Data Index: 1010956 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6700. Min Act: -0.0000

Data Index: 379980 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6200. Min Act: -0.0000

Data Index: 577193 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.6808. Min Act: -0.0000

Data Index: 348386 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.4998. Min Act: -0.0000

Data Index: 523688 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.5250. Min Act: -0.0000

Data Index: 339996 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.5004. Min Act: -0.0000

Data Index: 172600 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.4746. Min Act: -0.0000

Data Index: 3972 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.4908. Min Act: -0.0000

Data Index: 959048 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1170054 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1356137 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.4142. Min Act: -0.0000

Data Index: 235758 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.4928. Min Act: -0.0000

Data Index: 733907 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.8539. Min Range: -0.8539

Max Act: 0.4730. Min Act: -0.0000

Data Index: 817856 (C4 (Web Text))

Max Activating Token Index: 93