Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4497 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.8187. Min Act: -0.0000

Data Index: 119775 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.7691. Min Act: -0.0000

Data Index: 133140 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.7549. Min Act: -0.0000

Data Index: 477036 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.6642. Min Act: -0.0000

Data Index: 238458 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5814. Min Act: -0.0000

Data Index: 631863 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5953. Min Act: -0.0000

Data Index: 577551 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5729. Min Act: -0.0000

Data Index: 898761 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1003078 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5558. Min Act: -0.0000

Data Index: 1305004 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5442. Min Act: -0.0000

Data Index: 819196 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5336. Min Act: -0.0000

Data Index: 82378 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5096. Min Act: -0.0000

Data Index: 831546 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4876. Min Act: -0.0000

Data Index: 846646 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4979. Min Act: -0.0000

Data Index: 895286 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5093. Min Act: -0.0000

Data Index: 219870 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5097. Min Act: -0.0000

Data Index: 126815 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5292. Min Act: -0.0000

Data Index: 683723 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1167170 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.5240. Min Act: -0.0000

Data Index: 997827 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.8187. Min Range: -0.8187

Max Act: 0.4965. Min Act: -0.0000

Data Index: 529524 (C4 (Web Text))

Max Activating Token Index: 348