Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3609 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0757. Min Act: -0.0001

Data Index: 26100 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0563. Min Act: -0.0001

Data Index: 1204304 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1090159 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0273. Min Act: -0.0001

Data Index: 418553 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0522. Min Act: -0.0001

Data Index: 1068508 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0228. Min Act: -0.0001

Data Index: 1196464 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9832. Min Act: -0.0001

Data Index: 729828 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0423. Min Act: -0.0001

Data Index: 444822 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0099. Min Act: -0.0001

Data Index: 830192 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0022. Min Act: -0.0001

Data Index: 41747 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1312187 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9828. Min Act: -0.0001

Data Index: 728015 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9802. Min Act: -0.0001

Data Index: 1024097 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9483. Min Act: -0.0001

Data Index: 1117394 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9671. Min Act: -0.0001

Data Index: 391071 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.0903. Min Range: -1.0903

Max Act: 1.0343. Min Act: -0.0001

Data Index: 304349 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9288. Min Act: -0.0001

Data Index: 526600 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9289. Min Act: -0.0001

Data Index: 149822 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9781. Min Act: -0.0001

Data Index: 356774 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.0903. Min Range: -1.0903

Max Act: 0.9462. Min Act: -0.0001

Data Index: 26796 (C4 (Web Text))

Max Activating Token Index: 335