Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3636 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0002

Data Index: 669262 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0519. Min Act: -0.0002

Data Index: 917314 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1028917 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0501. Min Act: -0.0002

Data Index: 130830 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1040950 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1587428 (Python Code)

Max Activating Token Index: 480

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0525. Min Act: -0.0002

Data Index: 84905 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0474. Min Act: -0.0002

Data Index: 401882 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0505. Min Act: -0.0002

Data Index: 605255 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0511. Min Act: -0.0002

Data Index: 304306 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0465. Min Act: -0.0002

Data Index: 512814 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0485. Min Act: -0.0002

Data Index: 26014 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0475. Min Act: -0.0002

Data Index: 729683 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0462. Min Act: -0.0002

Data Index: 357343 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0489. Min Act: -0.0002

Data Index: 586195 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0506. Min Act: -0.0002

Data Index: 479330 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0503. Min Act: -0.0002

Data Index: 291164 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0434. Min Act: -0.0002

Data Index: 639140 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0443. Min Act: -0.0002

Data Index: 326829 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0434. Min Act: -0.0002

Data Index: 451248 (C4 (Web Text))

Max Activating Token Index: 54