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

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

Neuron 3700 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.1914. Min Act: -0.0001

Data Index: 1056717 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8499. Min Act: -0.0001

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9197. Min Act: -0.0001

Data Index: 1169057 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8498. Min Act: -0.0001

Data Index: 732964 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8433. Min Act: -0.0001

Data Index: 873254 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8412. Min Act: -0.0001

Data Index: 1156233 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8120. Min Act: -0.0001

Data Index: 972130 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8462. Min Act: -0.0001

Data Index: 726767 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8049. Min Act: -0.0001

Data Index: 625863 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8154. Min Act: -0.0001

Data Index: 1136124 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8056. Min Act: -0.0001

Data Index: 642816 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8258. Min Act: -0.0001

Data Index: 521070 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8126. Min Act: -0.0001

Data Index: 323765 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7528. Min Act: -0.0001

Data Index: 1141326 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7998. Min Act: -0.0001

Data Index: 23892 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7281. Min Act: -0.0001

Data Index: 825085 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7676. Min Act: -0.0001

Data Index: 1108719 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8143. Min Act: -0.0001

Data Index: 535748 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8236. Min Act: -0.0001

Data Index: 961741 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.7676. Min Act: -0.0001

Data Index: 686882 (C4 (Web Text))

Max Activating Token Index: 1004