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

Dataset: The Pile

Neuron 3440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6508. Min Act: -0.0000

Data Index: 1073037 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.9712. Min Act: -0.0000

Data Index: 1240166 (The Pile)

Max Activating Token Index: 346

Text #2

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6744. Min Act: -0.0000

Data Index: 1280757 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6462. Min Act: -0.0000

Data Index: 1717825 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6639. Min Act: -0.0000

Data Index: 639241 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6404. Min Act: -0.0000

Data Index: 1695524 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6352. Min Act: -0.0000

Data Index: 372919 (The Pile)

Max Activating Token Index: 303

Text #7

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.4537. Min Act: -0.0000

Data Index: 1220827 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6245. Min Act: -0.0000

Data Index: 1069561 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.5736. Min Act: -0.0000

Data Index: 1887628 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.5647. Min Act: -0.0000

Data Index: 428050 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.5707. Min Act: -0.0000

Data Index: 1202760 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.5238. Min Act: -0.0000

Data Index: 1225737 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.4962. Min Act: -0.0000

Data Index: 142620 (The Pile)

Max Activating Token Index: 276

Text #14

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.4746. Min Act: -0.0000

Data Index: 812357 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6052. Min Act: -0.0000

Data Index: 146964 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.6226. Min Act: -0.0000

Data Index: 1262572 (The Pile)

Max Activating Token Index: 598

Text #17

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.4517. Min Act: -0.0000

Data Index: 1084599 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.4499. Min Act: -0.0000

Data Index: 1447444 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 3.9712. Min Range: -3.9712

Max Act: 3.4563. Min Act: -0.0000

Data Index: 964576 (The Pile)

Max Activating Token Index: 599