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

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

Neuron 1893 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0002

Data Index: 696081 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1131. Min Act: -0.0002

Data Index: 968147 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1120. Min Act: -0.0002

Data Index: 842877 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1164. Min Act: -0.0002

Data Index: 660306 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1111. Min Act: -0.0002

Data Index: 256612 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1002. Min Act: -0.0002

Data Index: 758616 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1042417 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0977. Min Act: -0.0002

Data Index: 506704 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1045. Min Act: -0.0002

Data Index: 115847 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1141. Min Act: -0.0002

Data Index: 849612 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0998. Min Act: -0.0002

Data Index: 418107 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0992. Min Act: -0.0002

Data Index: 78019 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1052. Min Act: -0.0002

Data Index: 455540 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1036. Min Act: -0.0002

Data Index: 168137 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1026. Min Act: -0.0002

Data Index: 883275 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1062. Min Act: -0.0002

Data Index: 324504 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1033. Min Act: -0.0002

Data Index: 880120 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1010299 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1156774 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0980. Min Act: -0.0002

Data Index: 941293 (C4 (Web Text))

Max Activating Token Index: 806