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

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

Neuron 3819 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.9078. Min Act: -0.0001

Data Index: 871916 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.8092. Min Act: -0.0000

Data Index: 317880 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7516. Min Act: -0.0001

Data Index: 920131 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7617. Min Act: -0.0001

Data Index: 579727 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7050. Min Act: -0.0000

Data Index: 642276 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6865. Min Act: -0.0000

Data Index: 963613 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1153654 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1351175 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6793. Min Act: -0.0000

Data Index: 192183 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1061447 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1068220 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6857. Min Act: -0.0001

Data Index: 1024592 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.7074. Min Act: -0.0001

Data Index: 1113833 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6408. Min Act: -0.0001

Data Index: 1009830 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6361. Min Act: -0.0001

Data Index: 250452 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6553. Min Act: -0.0000

Data Index: 898732 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6737. Min Act: -0.0000

Data Index: 902931 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6717. Min Act: -0.0000

Data Index: 938172 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6498. Min Act: -0.0000

Data Index: 88751 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.9078. Min Range: -0.9078

Max Act: 0.6261. Min Act: -0.0000

Data Index: 207210 (C4 (Web Text))

Max Activating Token Index: 406