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

Dataset: The Pile

Neuron 4192 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: 0.9656. Min Range: -0.9656

Max Act: 0.9656. Min Act: -0.0000

Data Index: 177684 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1410471 (The Pile)

Max Activating Token Index: 784

Text #2

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7198. Min Act: -0.0000

Data Index: 344623 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1753609 (The Pile)

Max Activating Token Index: 319

Text #4

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7691. Min Act: -0.0000

Data Index: 1648691 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1800966 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1632840 (The Pile)

Max Activating Token Index: 338

Text #7

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1190904 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1005558 (The Pile)

Max Activating Token Index: 136

Text #9

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6559. Min Act: -0.0000

Data Index: 647975 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6794. Min Act: -0.0000

Data Index: 225760 (The Pile)

Max Activating Token Index: 328

Text #11

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6965. Min Act: -0.0000

Data Index: 788376 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6793. Min Act: -0.0000

Data Index: 724273 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6534. Min Act: -0.0000

Data Index: 654621 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6496. Min Act: -0.0000

Data Index: 207556 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1487512 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6921. Min Act: -0.0000

Data Index: 722655 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6283. Min Act: -0.0000

Data Index: 791390 (The Pile)

Max Activating Token Index: 342

Text #18

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.7187. Min Act: -0.0000

Data Index: 390510 (The Pile)

Max Activating Token Index: 463

Text #19

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1351723 (The Pile)

Max Activating Token Index: 504