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

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

Neuron 688 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1608. Min Act: -0.0004

Data Index: 296977 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1313. Min Act: -0.0004

Data Index: 302740 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1315. Min Act: -0.0004

Data Index: 202105 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1222. Min Act: -0.0004

Data Index: 591447 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.1137. Min Act: -0.0004

Data Index: 600033 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0993. Min Act: -0.0004

Data Index: 1046841 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0992. Min Act: -0.0004

Data Index: 1121683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0935. Min Act: -0.0004

Data Index: 975551 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0904. Min Act: -0.0004

Data Index: 838563 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0922. Min Act: -0.0004

Data Index: 612337 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0898. Min Act: -0.0004

Data Index: 126195 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0912. Min Act: -0.0004

Data Index: 100876 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0861. Min Act: -0.0004

Data Index: 85598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0852. Min Act: -0.0004

Data Index: 116084 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0867. Min Act: -0.0004

Data Index: 636412 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0883. Min Act: -0.0004

Data Index: 570777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0837. Min Act: -0.0004

Data Index: 482769 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0823. Min Act: -0.0004

Data Index: 850202 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0832. Min Act: -0.0004

Data Index: 1622199 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.1608. Min Range: -0.1608

Max Act: 0.0834. Min Act: -0.0004

Data Index: 872927 (C4 (Web Text))

Max Activating Token Index: 1023