Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2024 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1294. Min Act: -0.0003

Data Index: 215737 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1169. Min Act: -0.0003

Data Index: 1309855 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1155. Min Act: -0.0003

Data Index: 408253 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1124. Min Act: -0.0003

Data Index: 822810 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1068. Min Act: -0.0004

Data Index: 601037 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1058. Min Act: -0.0003

Data Index: 726019 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1110. Min Act: -0.0003

Data Index: 1160003 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1011. Min Act: -0.0003

Data Index: 440583 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1049. Min Act: -0.0003

Data Index: 694508 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1012. Min Act: -0.0004

Data Index: 716708 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1300608 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0964. Min Act: -0.0003

Data Index: 746151 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0926. Min Act: -0.0003

Data Index: 1337797 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0960. Min Act: -0.0003

Data Index: 13023 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0988. Min Act: -0.0003

Data Index: 348773 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0950. Min Act: -0.0003

Data Index: 449490 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0989. Min Act: -0.0003

Data Index: 1072629 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.1020. Min Act: -0.0003

Data Index: 939891 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0974. Min Act: -0.0003

Data Index: 258133 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.1294. Min Range: -0.1294

Max Act: 0.0977. Min Act: -0.0003

Data Index: 774760 (C4 (Web Text))

Max Activating Token Index: 539