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

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

Neuron 1199 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7734. Min Act: -0.0001

Data Index: 933426 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6582. Min Act: -0.0001

Data Index: 1309594 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7414. Min Act: -0.0001

Data Index: 1168495 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6542. Min Act: -0.0001

Data Index: 190340 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6462. Min Act: -0.0001

Data Index: 1158589 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6515. Min Act: -0.0001

Data Index: 907194 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6124. Min Act: -0.0001

Data Index: 48858 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6622. Min Act: -0.0001

Data Index: 629102 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6438. Min Act: -0.0001

Data Index: 126922 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6728. Min Act: -0.0001

Data Index: 41214 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6595. Min Act: -0.0001

Data Index: 789857 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6195. Min Act: -0.0001

Data Index: 653698 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6616. Min Act: -0.0001

Data Index: 1299352 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6761. Min Act: -0.0001

Data Index: 218898 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5746. Min Act: -0.0001

Data Index: 1206416 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6985. Min Act: -0.0001

Data Index: 432494 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5947. Min Act: -0.0001

Data Index: 1331294 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6081. Min Act: -0.0001

Data Index: 797047 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6222. Min Act: -0.0001

Data Index: 560385 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6182. Min Act: -0.0001

Data Index: 1127486 (C4 (Web Text))

Max Activating Token Index: 702