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

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

Neuron 3506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2396. Min Range: -1.2396

Max Act: 1.2396. Min Act: -0.0000

Data Index: 1227445 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 1.2396. Min Range: -1.2396

Max Act: 1.0430. Min Act: -0.0000

Data Index: 126897 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.8729. Min Act: -0.0000

Data Index: 886044 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9618. Min Act: -0.0000

Data Index: 810358 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 1.2396. Min Range: -1.2396

Max Act: 1.0256. Min Act: -0.0000

Data Index: 512972 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9622. Min Act: -0.0000

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9957. Min Act: -0.0000

Data Index: 449413 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1352155 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9081. Min Act: -0.0000

Data Index: 908913 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9576. Min Act: -0.0000

Data Index: 496643 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1074759 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1208870 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.8820. Min Act: -0.0000

Data Index: 945959 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.8749. Min Act: -0.0000

Data Index: 178618 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.8727. Min Act: -0.0000

Data Index: 289237 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.8763. Min Act: -0.0000

Data Index: 382015 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.7740. Min Act: -0.0000

Data Index: 119491 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9460. Min Act: -0.0000

Data Index: 582234 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.9136. Min Act: -0.0000

Data Index: 137070 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.2396. Min Range: -1.2396

Max Act: 0.8447. Min Act: -0.0000

Data Index: 366780 (C4 (Web Text))

Max Activating Token Index: 462