Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 214 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.8840. Min Act: -0.0004

Data Index: 1189755 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7506. Min Act: -0.0003

Data Index: 589373 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7678. Min Act: -0.0003

Data Index: 846931 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7494. Min Act: -0.0004

Data Index: 888115 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6923. Min Act: -0.0003

Data Index: 1168543 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6938. Min Act: -0.0003

Data Index: 442126 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7380. Min Act: -0.0004

Data Index: 1177759 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7100. Min Act: -0.0003

Data Index: 740147 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6667. Min Act: -0.0003

Data Index: 175699 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7535. Min Act: -0.0003

Data Index: 1224764 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7413. Min Act: -0.0003

Data Index: 1062200 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7130. Min Act: -0.0003

Data Index: 539201 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6885. Min Act: -0.0003

Data Index: 1201604 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6472. Min Act: -0.0003

Data Index: 780854 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7236. Min Act: -0.0004

Data Index: 293187 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6805. Min Act: -0.0003

Data Index: 534796 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6569. Min Act: -0.0003

Data Index: 593432 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6093. Min Act: -0.0003

Data Index: 783334 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.7047. Min Act: -0.0003

Data Index: 643188 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.8840. Min Range: -0.8840

Max Act: 0.6805. Min Act: -0.0003

Data Index: 1035404 (C4 (Web Text))

Max Activating Token Index: 763