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

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

Neuron 1031 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: 0.9141. Min Range: -0.9141

Max Act: 0.9141. Min Act: -0.0000

Data Index: 308194 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7980. Min Act: -0.0000

Data Index: 312645 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1278773 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6744. Min Act: -0.0000

Data Index: 339445 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6782. Min Act: -0.0000

Data Index: 894753 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1187485 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1319983 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6080. Min Act: -0.0000

Data Index: 629207 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.6612. Min Act: -0.0000

Data Index: 77796 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1131266 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5357. Min Act: -0.0000

Data Index: 1091650 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5855. Min Act: -0.0000

Data Index: 331180 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5249. Min Act: -0.0000

Data Index: 232955 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5178. Min Act: -0.0000

Data Index: 880813 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.4736. Min Act: -0.0000

Data Index: 250124 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.4862. Min Act: -0.0000

Data Index: 903581 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1065546 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1029747 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5008. Min Act: -0.0000

Data Index: 137820 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.9141. Min Range: -0.9141

Max Act: 0.5001. Min Act: -0.0000

Data Index: 988192 (C4 (Web Text))

Max Activating Token Index: 318