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

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

Neuron 4716 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0770. Min Range: -2.0770

Max Act: 2.0770. Min Act: -0.0000

Data Index: 651473 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.7563. Min Act: -0.0000

Data Index: 1346117 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.7384. Min Act: -0.0000

Data Index: 1055863 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.7551. Min Act: -0.0000

Data Index: 522567 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.5294. Min Act: -0.0000

Data Index: 640899 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.5389. Min Act: -0.0000

Data Index: 992423 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.6164. Min Act: -0.0000

Data Index: 121112 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.4914. Min Act: -0.0000

Data Index: 46376 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.3790. Min Act: -0.0000

Data Index: 200479 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.3754. Min Act: -0.0000

Data Index: 982348 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.2761. Min Act: -0.0000

Data Index: 761550 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.2576. Min Act: -0.0000

Data Index: 124420 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.2561. Min Act: -0.0000

Data Index: 448437 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.3321. Min Act: -0.0000

Data Index: 622038 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.3088. Min Act: -0.0000

Data Index: 813248 (C4 (Web Text))

Max Activating Token Index: 413

Text #15

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.2886. Min Act: -0.0000

Data Index: 486338 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.3442. Min Act: -0.0000

Data Index: 877735 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.2632. Min Act: -0.0000

Data Index: 701349 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.2623. Min Act: -0.0000

Data Index: 1126938 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 2.0770. Min Range: -2.0770

Max Act: 1.2714. Min Act: -0.0000

Data Index: 43048 (C4 (Web Text))

Max Activating Token Index: 63