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

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

Neuron 4858 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0695. Min Range: -4.0695

Max Act: 4.0695. Min Act: -0.0000

Data Index: 462017 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.6372. Min Act: -0.0000

Data Index: 569305 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.7365. Min Act: -0.0000

Data Index: 367542 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.8918. Min Act: -0.0000

Data Index: 705576 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.5346. Min Act: -0.0000

Data Index: 688363 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.6770. Min Act: -0.0000

Data Index: 792851 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 4.0695. Min Range: -4.0695

Max Act: 2.9934. Min Act: -0.0000

Data Index: 824324 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.2199. Min Act: -0.0000

Data Index: 329327 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.1814. Min Act: -0.0000

Data Index: 795218 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.3412. Min Act: -0.0000

Data Index: 236083 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.4888. Min Act: -0.0000

Data Index: 743153 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.0302. Min Act: -0.0000

Data Index: 1313217 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.3359. Min Act: -0.0000

Data Index: 254058 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.4629. Min Act: -0.0000

Data Index: 553292 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 4.0695. Min Range: -4.0695

Max Act: 2.9950. Min Act: -0.0000

Data Index: 16769 (C4 (Web Text))

Max Activating Token Index: 231

Text #15

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.1888. Min Act: -0.0000

Data Index: 219876 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 4.0695. Min Range: -4.0695

Max Act: 3.0141. Min Act: -0.0000

Data Index: 697220 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 4.0695. Min Range: -4.0695

Max Act: 2.8781. Min Act: -0.0000

Data Index: 189261 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 4.0695. Min Range: -4.0695

Max Act: 2.8645. Min Act: -0.0000

Data Index: 809592 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 4.0695. Min Range: -4.0695

Max Act: 2.8654. Min Act: -0.0000

Data Index: 648797 (C4 (Web Text))

Max Activating Token Index: 422