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

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

Neuron 3954 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.8840. Min Act: -0.0000

Data Index: 1106300 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.7256. Min Act: -0.0000

Data Index: 791289 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.7361. Min Act: -0.0000

Data Index: 1276177 (C4 (Web Text))

Max Activating Token Index: 268

Text #3

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.5014. Min Act: -0.0000

Data Index: 33678 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.4995. Min Act: -0.0000

Data Index: 1079188 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.4633. Min Act: -0.0000

Data Index: 1312834 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.4130. Min Act: -0.0000

Data Index: 1100655 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.4686. Min Act: -0.0000

Data Index: 863131 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.4238. Min Act: -0.0000

Data Index: 777769 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.4960. Min Act: -0.0000

Data Index: 1248879 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.3400. Min Act: -0.0000

Data Index: 88099 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.2167. Min Act: -0.0000

Data Index: 223054 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.0267. Min Act: -0.0000

Data Index: 1058836 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.1547. Min Act: -0.0000

Data Index: 1232858 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.8175. Min Act: -0.0000

Data Index: 439743 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.3893. Min Act: -0.0000

Data Index: 113093 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.7581. Min Act: -0.0000

Data Index: 1141617 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.3102. Min Act: -0.0000

Data Index: 365466 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 2.8840. Min Range: -2.8840

Max Act: 1.9999. Min Act: -0.0000

Data Index: 881340 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 2.8840. Min Range: -2.8840

Max Act: 2.0921. Min Act: -0.0000

Data Index: 649443 (C4 (Web Text))

Max Activating Token Index: 604