Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3185 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1288279 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1148. Min Act: -0.0001

Data Index: 865852 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1082. Min Act: -0.0001

Data Index: 638114 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1092. Min Act: -0.0001

Data Index: 252269 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1174. Min Act: -0.0002

Data Index: 18465 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1097. Min Act: -0.0001

Data Index: 416418 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1053. Min Act: -0.0002

Data Index: 555040 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1102. Min Act: -0.0002

Data Index: 290065 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1037. Min Act: -0.0001

Data Index: 616847 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1053694 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1195745 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1009. Min Act: -0.0001

Data Index: 572717 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.1000. Min Act: -0.0001

Data Index: 860586 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0969. Min Act: -0.0001

Data Index: 1062432 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0966. Min Act: -0.0002

Data Index: 380339 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1353095 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0990. Min Act: -0.0001

Data Index: 699283 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0991. Min Act: -0.0002

Data Index: 578226 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0914. Min Act: -0.0002

Data Index: 193490 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.1324. Min Range: -0.1324

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1145603 (C4 (Web Text))

Max Activating Token Index: 124