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

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

Neuron 6105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1109 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.7116. Min Act: -0.0000

Data Index: 992521 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6945. Min Act: -0.0000

Data Index: 65391 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6813. Min Act: -0.0000

Data Index: 362830 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6733. Min Act: -0.0000

Data Index: 236578 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6787. Min Act: -0.0000

Data Index: 23139 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6584. Min Act: -0.0000

Data Index: 922971 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6333. Min Act: -0.0000

Data Index: 666665 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6123. Min Act: -0.0000

Data Index: 469191 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1143847 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5667. Min Act: -0.0000

Data Index: 595535 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6043. Min Act: -0.0000

Data Index: 318356 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.6010. Min Act: -0.0000

Data Index: 948081 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5346. Min Act: -0.0000

Data Index: 768270 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5344. Min Act: -0.0000

Data Index: 800287 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5361. Min Act: -0.0000

Data Index: 601638 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5526. Min Act: -0.0000

Data Index: 131717 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1096397 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5301. Min Act: -0.0000

Data Index: 591925 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.7619. Min Range: -0.7619

Max Act: 0.5644. Min Act: -0.0000

Data Index: 460828 (C4 (Web Text))

Max Activating Token Index: 314