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

Dataset: The Pile

Neuron 1495 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: 1.2343. Min Range: -1.2343

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1968308 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 1.2343. Min Range: -1.2343

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1439000 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 1.2343. Min Range: -1.2343

Max Act: 1.0438. Min Act: -0.0000

Data Index: 522165 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1827025 (The Pile)

Max Activating Token Index: 342

Text #4

Max Range: 1.2343. Min Range: -1.2343

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1960071 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 1.2343. Min Range: -1.2343

Max Act: 1.0267. Min Act: -0.0000

Data Index: 1955946 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8948. Min Act: -0.0000

Data Index: 1278241 (The Pile)

Max Activating Token Index: 968

Text #7

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9453. Min Act: -0.0000

Data Index: 227176 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9789. Min Act: -0.0000

Data Index: 655485 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9320. Min Act: -0.0000

Data Index: 5451 (The Pile)

Max Activating Token Index: 458

Text #10

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8624. Min Act: -0.0000

Data Index: 939781 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9477. Min Act: -0.0000

Data Index: 16893 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1243504 (The Pile)

Max Activating Token Index: 503

Text #13

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8854. Min Act: -0.0000

Data Index: 204090 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8316. Min Act: -0.0000

Data Index: 607105 (The Pile)

Max Activating Token Index: 780

Text #15

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8310. Min Act: 0.0000

Data Index: 1294292 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1651889 (The Pile)

Max Activating Token Index: 391

Text #17

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.9079. Min Act: -0.0000

Data Index: 332991 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8421. Min Act: -0.0000

Data Index: 597573 (The Pile)

Max Activating Token Index: 626

Text #19

Max Range: 1.2343. Min Range: -1.2343

Max Act: 0.8495. Min Act: -0.0000

Data Index: 406222 (The Pile)

Max Activating Token Index: 451