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

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

Neuron 1350 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1274. Min Act: -0.0001

Data Index: 168602 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1265. Min Act: -0.0001

Data Index: 103098 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1055. Min Act: -0.0001

Data Index: 633659 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1543801 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1014489 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1042. Min Act: -0.0001

Data Index: 960807 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1628426 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1018. Min Act: -0.0001

Data Index: 812564 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1052. Min Act: -0.0001

Data Index: 316097 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1036. Min Act: -0.0001

Data Index: 547502 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1041. Min Act: -0.0001

Data Index: 1026698 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1187101 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1014776 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1451486 (Python Code)

Max Activating Token Index: 277

Text #14

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0998. Min Act: -0.0001

Data Index: 324746 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1033. Min Act: -0.0001

Data Index: 452025 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.1008. Min Act: -0.0001

Data Index: 99680 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1459680 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0919. Min Act: -0.0001

Data Index: 806055 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 0.1274. Min Range: -0.1274

Max Act: 0.0992. Min Act: -0.0001

Data Index: 822274 (C4 (Web Text))

Max Activating Token Index: 300