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

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

Neuron 4937 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: 0.5648. Min Range: -0.5648

Max Act: 0.5648. Min Act: -0.0000

Data Index: 307038 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5283. Min Act: -0.0000

Data Index: 242161 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5579. Min Act: -0.0000

Data Index: 88801 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5406. Min Act: -0.0000

Data Index: 167492 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5346. Min Act: -0.0000

Data Index: 174393 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4859. Min Act: -0.0000

Data Index: 651857 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4954. Min Act: -0.0000

Data Index: 473530 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4896. Min Act: -0.0000

Data Index: 787762 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.5020. Min Act: -0.0000

Data Index: 845648 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1305426 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4791. Min Act: -0.0000

Data Index: 137665 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4915. Min Act: -0.0000

Data Index: 815904 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4695. Min Act: -0.0000

Data Index: 419332 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1063343 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4654. Min Act: -0.0000

Data Index: 1047703 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4405. Min Act: -0.0000

Data Index: 448704 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4640. Min Act: -0.0000

Data Index: 377577 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1297265 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4599. Min Act: -0.0000

Data Index: 658584 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.5648. Min Range: -0.5648

Max Act: 0.4442. Min Act: -0.0000

Data Index: 217493 (C4 (Web Text))

Max Activating Token Index: 920