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

Dataset: The Pile

Neuron 4623 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: 1.8529. Min Range: -1.8529

Max Act: 1.8529. Min Act: -0.0000

Data Index: 342615 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.8194. Min Act: -0.0000

Data Index: 1624659 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.7056. Min Act: -0.0000

Data Index: 1341877 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.8073. Min Act: -0.0000

Data Index: 37822 (The Pile)

Max Activating Token Index: 628

Text #4

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.4260. Min Act: -0.0000

Data Index: 755135 (The Pile)

Max Activating Token Index: 489

Text #5

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.4919. Min Act: -0.0000

Data Index: 830918 (The Pile)

Max Activating Token Index: 814

Text #6

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.6390. Min Act: -0.0000

Data Index: 522858 (The Pile)

Max Activating Token Index: 751

Text #7

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.5194. Min Act: -0.0000

Data Index: 133596 (The Pile)

Max Activating Token Index: 960

Text #8

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.4351. Min Act: -0.0000

Data Index: 482239 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.4570. Min Act: 0.0000

Data Index: 1393705 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.5129. Min Act: -0.0000

Data Index: 1083392 (The Pile)

Max Activating Token Index: 861

Text #11

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.3790. Min Act: -0.0000

Data Index: 801195 (The Pile)

Max Activating Token Index: 708

Text #12

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.4171. Min Act: -0.0000

Data Index: 165021 (The Pile)

Max Activating Token Index: 889

Text #13

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.3237. Min Act: -0.0000

Data Index: 681944 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1964876 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.2685. Min Act: -0.0000

Data Index: 545875 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1537556 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1306388 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.3538. Min Act: -0.0000

Data Index: 781630 (The Pile)

Max Activating Token Index: 336

Text #19

Max Range: 1.8529. Min Range: -1.8529

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1077908 (The Pile)

Max Activating Token Index: 778