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

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

Neuron 4662 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: 0.0108. Min Range: -0.0108

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1233096 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0105. Min Act: -0.0002

Data Index: 783877 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0102. Min Act: -0.0003

Data Index: 264693 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0002

Data Index: 1264017 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0097. Min Act: -0.0002

Data Index: 652070 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0095. Min Act: -0.0003

Data Index: 690276 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0099. Min Act: -0.0003

Data Index: 148423 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0090. Min Act: -0.0003

Data Index: 395948 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1254192 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0002

Data Index: 838562 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0088. Min Act: -0.0003

Data Index: 584824 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0002

Data Index: 1351659 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0088. Min Act: -0.0003

Data Index: 556351 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0087. Min Act: -0.0003

Data Index: 296365 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0095. Min Act: -0.0003

Data Index: 1257353 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0085. Min Act: -0.0003

Data Index: 1315936 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0089. Min Act: -0.0003

Data Index: 541473 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0087. Min Act: -0.0003

Data Index: 910867 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0085. Min Act: -0.0003

Data Index: 174178 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1107563 (C4 (Web Text))

Max Activating Token Index: 10