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

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

Neuron 5063 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1067. Min Act: -0.0000

Data Index: 731617 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1058. Min Act: -0.0000

Data Index: 853295 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1071. Min Act: -0.0000

Data Index: 642300 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1141875 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1036. Min Act: -0.0000

Data Index: 989775 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1034312 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1026. Min Act: -0.0000

Data Index: 130908 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1180810 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0982. Min Act: -0.0000

Data Index: 579255 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1130802 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1007. Min Act: -0.0000

Data Index: 171951 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1010. Min Act: -0.0000

Data Index: 656459 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.1031. Min Act: -0.0000

Data Index: 708408 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0985. Min Act: -0.0000

Data Index: 859386 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1222686 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1212931 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0950. Min Act: -0.0000

Data Index: 464959 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0963. Min Act: -0.0000

Data Index: 162887 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1215082 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.1071. Min Range: -0.1071

Max Act: 0.0950. Min Act: -0.0000

Data Index: 516579 (C4 (Web Text))

Max Activating Token Index: 281