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

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

Neuron 726 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1857. Min Range: -1.1857

Max Act: 1.1857. Min Act: -0.0000

Data Index: 37347 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 1.1857. Min Range: -1.1857

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1076845 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.1857. Min Range: -1.1857

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1240286 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 1.1857. Min Range: -1.1857

Max Act: 1.0150. Min Act: -0.0000

Data Index: 343254 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.1857. Min Range: -1.1857

Max Act: 1.0084. Min Act: -0.0000

Data Index: 155492 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1268386 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1233468 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.8534. Min Act: -0.0000

Data Index: 351608 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 1.1857. Min Range: -1.1857

Max Act: 1.0403. Min Act: -0.0000

Data Index: 308964 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.9095. Min Act: -0.0000

Data Index: 416253 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.8458. Min Act: -0.0000

Data Index: 670638 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.9473. Min Act: -0.0000

Data Index: 816404 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1316980 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.8754. Min Act: -0.0000

Data Index: 273728 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.8453. Min Act: -0.0000

Data Index: 250527 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.8103. Min Act: -0.0000

Data Index: 1221205 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.7582. Min Act: -0.0000

Data Index: 519538 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.9357. Min Act: -0.0000

Data Index: 24633 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.7196. Min Act: -0.0000

Data Index: 9458 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 1.1857. Min Range: -1.1857

Max Act: 0.7605. Min Act: -0.0000

Data Index: 445067 (C4 (Web Text))

Max Activating Token Index: 437