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

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

Neuron 3323 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: 0.1556. Min Range: -0.1556

Max Act: 0.1556. Min Act: -0.0000

Data Index: 342075 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1514. Min Act: -0.0000

Data Index: 161865 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1410. Min Act: -0.0000

Data Index: 683625 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1300. Min Act: -0.0000

Data Index: 628950 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1466. Min Act: -0.0000

Data Index: 559404 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1305. Min Act: -0.0000

Data Index: 130399 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1212. Min Act: -0.0000

Data Index: 995363 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1153. Min Act: -0.0000

Data Index: 117344 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1354115 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1178. Min Act: -0.0000

Data Index: 437499 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1130. Min Act: -0.0000

Data Index: 846129 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1235860 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1134. Min Act: -0.0000

Data Index: 3466 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1047. Min Act: -0.0000

Data Index: 868779 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1266736 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1079. Min Act: -0.0000

Data Index: 797380 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1033. Min Act: -0.0000

Data Index: 48799 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1096. Min Act: -0.0000

Data Index: 848849 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1023. Min Act: -0.0000

Data Index: 313108 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1021. Min Act: -0.0000

Data Index: 784382 (C4 (Web Text))

Max Activating Token Index: 376