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

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

Neuron 780 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: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0004

Data Index: 277004 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1158. Min Act: -0.0004

Data Index: 423616 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1138. Min Act: -0.0004

Data Index: 891690 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0992. Min Act: -0.0004

Data Index: 1135137 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0955. Min Act: -0.0004

Data Index: 763944 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1199. Min Act: -0.0004

Data Index: 1014631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1209. Min Act: -0.0004

Data Index: 93073 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1064. Min Act: -0.0004

Data Index: 612994 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0960. Min Act: -0.0004

Data Index: 1301477 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1015. Min Act: -0.0004

Data Index: 46648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1185. Min Act: -0.0004

Data Index: 988558 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0839. Min Act: -0.0004

Data Index: 252472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0880. Min Act: -0.0004

Data Index: 856679 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1034. Min Act: -0.0004

Data Index: 158007 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1289. Min Act: -0.0004

Data Index: 1014604 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0937. Min Act: -0.0004

Data Index: 69078 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0867. Min Act: -0.0004

Data Index: 370889 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1050. Min Act: -0.0004

Data Index: 17440 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1012. Min Act: -0.0004

Data Index: 314796 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0965. Min Act: -0.0004

Data Index: 29608 (C4 (Web Text))

Max Activating Token Index: 1023