Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3600 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0885. Min Range: -1.0885

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1082950 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.7336. Min Act: -0.0000

Data Index: 945124 (C4 (Web Text))

Max Activating Token Index: 420

Text #2

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.6977. Min Act: -0.0000

Data Index: 706358 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1494812 (Python Code)

Max Activating Token Index: 455

Text #4

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1617676 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.6420. Min Act: -0.0000

Data Index: 870445 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.6069. Min Act: -0.0000

Data Index: 841796 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.5572. Min Act: -0.0000

Data Index: 863247 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.5063. Min Act: -0.0000

Data Index: 681901 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1651624 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1417040 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4839. Min Act: 0.0000

Data Index: 145397 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4912. Min Act: -0.0000

Data Index: 685693 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4964. Min Act: -0.0000

Data Index: 984905 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1172889 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4981. Min Act: -0.0000

Data Index: 784387 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1214638 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1070223 (C4 (Web Text))

Max Activating Token Index: 954

Text #18

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1306120 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.0885. Min Range: -1.0885

Max Act: 0.4563. Min Act: -0.0000

Data Index: 368156 (C4 (Web Text))

Max Activating Token Index: 806