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

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

Neuron 4133 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1091. Min Act: -0.0002

Data Index: 454203 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1117. Min Act: -0.0003

Data Index: 462531 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1148. Min Act: -0.0003

Data Index: 304458 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1118921 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1075. Min Act: -0.0003

Data Index: 1351361 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1023. Min Act: -0.0003

Data Index: 310726 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1030. Min Act: -0.0003

Data Index: 401729 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1030. Min Act: -0.0003

Data Index: 1152230 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1013. Min Act: -0.0003

Data Index: 1321333 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1015. Min Act: -0.0003

Data Index: 17828 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1005. Min Act: -0.0003

Data Index: 347867 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1000. Min Act: -0.0002

Data Index: 1039664 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.1001. Min Act: -0.0002

Data Index: 327817 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1214847 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1353909 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0985. Min Act: -0.0003

Data Index: 125607 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0955. Min Act: -0.0003

Data Index: 256021 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0973. Min Act: -0.0003

Data Index: 909018 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0973. Min Act: -0.0002

Data Index: 640919 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.1148. Min Range: -0.1148

Max Act: 0.0960. Min Act: -0.0002

Data Index: 830629 (C4 (Web Text))

Max Activating Token Index: 314