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

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

Neuron 4067 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0865. Min Act: -0.0000

Data Index: 930017 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1065423 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1241520 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1131286 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1251648 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0578. Min Act: -0.0001

Data Index: 191165 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0548. Min Act: -0.0001

Data Index: 1258821 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1168135 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1257744 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0545. Min Act: -0.0001

Data Index: 988273 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0530. Min Act: -0.0001

Data Index: 164500 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0476. Min Act: -0.0001

Data Index: 592187 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1310752 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0515. Min Act: -0.0001

Data Index: 333068 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1019551 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0512. Min Act: -0.0000

Data Index: 831237 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0508. Min Act: -0.0001

Data Index: 604902 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0515. Min Act: -0.0000

Data Index: 616612 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0498. Min Act: -0.0001

Data Index: 716342 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.0865. Min Range: -0.0865

Max Act: 0.0472. Min Act: -0.0000

Data Index: 365905 (C4 (Web Text))

Max Activating Token Index: 472