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

Dataset: The Pile

Neuron 1557 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1323. Min Range: -3.1323

Max Act: 3.0077. Min Act: -0.0000

Data Index: 1852730 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 3.1323. Min Range: -3.1323

Max Act: 3.1323. Min Act: -0.0000

Data Index: 1949811 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.8327. Min Act: -0.0000

Data Index: 1531694 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.6223. Min Act: -0.0000

Data Index: 305551 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.7781. Min Act: -0.0000

Data Index: 81378 (The Pile)

Max Activating Token Index: 151

Text #5

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.7983. Min Act: -0.0000

Data Index: 443074 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.6570. Min Act: -0.0000

Data Index: 279448 (The Pile)

Max Activating Token Index: 494

Text #7

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.6390. Min Act: -0.0000

Data Index: 1446416 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.6831. Min Act: -0.0000

Data Index: 543341 (The Pile)

Max Activating Token Index: 403

Text #9

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.4959. Min Act: -0.0000

Data Index: 637661 (The Pile)

Max Activating Token Index: 554

Text #10

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.6579. Min Act: -0.0000

Data Index: 859449 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.4100. Min Act: -0.0000

Data Index: 1309260 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.6433. Min Act: -0.0000

Data Index: 1850886 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.4594. Min Act: -0.0000

Data Index: 770246 (The Pile)

Max Activating Token Index: 712

Text #14

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.4849. Min Act: -0.0000

Data Index: 153497 (The Pile)

Max Activating Token Index: 730

Text #15

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.4597. Min Act: -0.0000

Data Index: 383210 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.4435. Min Act: -0.0000

Data Index: 113207 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.3982. Min Act: -0.0000

Data Index: 1270194 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.2781. Min Act: -0.0000

Data Index: 1535206 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 3.1323. Min Range: -3.1323

Max Act: 2.4429. Min Act: -0.0000

Data Index: 689104 (The Pile)

Max Activating Token Index: 742