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

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

Neuron 1708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6834. Min Act: -0.0000

Data Index: 906794 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6210. Min Act: -0.0000

Data Index: 620230 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5695. Min Act: -0.0000

Data Index: 245435 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5427. Min Act: -0.0000

Data Index: 778178 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5365. Min Act: -0.0000

Data Index: 605887 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5177. Min Act: -0.0000

Data Index: 901779 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4988. Min Act: -0.0000

Data Index: 295056 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4964. Min Act: -0.0000

Data Index: 140849 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4715. Min Act: -0.0000

Data Index: 229922 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5029. Min Act: -0.0000

Data Index: 809482 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4703. Min Act: -0.0000

Data Index: 247551 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5239. Min Act: -0.0000

Data Index: 824056 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4684. Min Act: -0.0000

Data Index: 293087 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1037187 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1251815 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4472. Min Act: -0.0000

Data Index: 678776 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4181. Min Act: -0.0000

Data Index: 422466 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4571. Min Act: -0.0000

Data Index: 644346 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1279061 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4677. Min Act: -0.0000

Data Index: 725510 (C4 (Web Text))

Max Activating Token Index: 129