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

Dataset: The Pile

Neuron 297 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: 1.7323. Min Range: -1.7323

Max Act: 1.7323. Min Act: -0.0000

Data Index: 921700 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.6781. Min Act: -0.0000

Data Index: 319285 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.6518. Min Act: -0.0000

Data Index: 1483698 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5582. Min Act: -0.0000

Data Index: 1809294 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.7156. Min Act: -0.0000

Data Index: 1043142 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5447. Min Act: -0.0000

Data Index: 612410 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.7150. Min Act: -0.0000

Data Index: 1579765 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.7176. Min Act: -0.0000

Data Index: 669390 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5074. Min Act: -0.0000

Data Index: 423128 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5949. Min Act: -0.0000

Data Index: 81667 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5643. Min Act: -0.0000

Data Index: 1810178 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5533. Min Act: -0.0000

Data Index: 960430 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5335. Min Act: -0.0000

Data Index: 1044519 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5923. Min Act: -0.0000

Data Index: 973979 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1681834 (The Pile)

Max Activating Token Index: 135

Text #15

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4281. Min Act: -0.0000

Data Index: 428615 (The Pile)

Max Activating Token Index: 963

Text #16

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5679. Min Act: -0.0000

Data Index: 154994 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4188. Min Act: -0.0000

Data Index: 765773 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4038. Min Act: -0.0000

Data Index: 928144 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4686. Min Act: -0.0000

Data Index: 1675205 (The Pile)

Max Activating Token Index: 249