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

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

Neuron 978 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.5840. Min Act: -0.0000

Data Index: 843818 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.5746. Min Act: -0.0000

Data Index: 480173 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.4779. Min Act: -0.0000

Data Index: 46578 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.5611. Min Act: -0.0000

Data Index: 912212 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.3154. Min Act: -0.0000

Data Index: 706042 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.0721. Min Act: -0.0000

Data Index: 559434 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.1824. Min Act: -0.0000

Data Index: 846170 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.9342. Min Act: -0.0000

Data Index: 965208 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.0236. Min Act: -0.0000

Data Index: 64232 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 2.5840. Min Range: -2.5840

Max Act: 2.1330. Min Act: -0.0000

Data Index: 1266567 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.8091. Min Act: -0.0000

Data Index: 969311 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.8953. Min Act: -0.0000

Data Index: 1345845 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.8059. Min Act: -0.0000

Data Index: 550289 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.8799. Min Act: -0.0000

Data Index: 923591 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.7762. Min Act: -0.0000

Data Index: 25921 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.7420. Min Act: -0.0000

Data Index: 266546 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.9030. Min Act: -0.0000

Data Index: 829803 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.7871. Min Act: -0.0000

Data Index: 866017 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.9701. Min Act: -0.0000

Data Index: 1030466 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 2.5840. Min Range: -2.5840

Max Act: 1.6413. Min Act: -0.0000

Data Index: 34017 (C4 (Web Text))

Max Activating Token Index: 432