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

Dataset: The Pile

Neuron 4216 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: 0.8630. Min Range: -0.8630

Max Act: 0.8615. Min Act: -0.0000

Data Index: 90658 (The Pile)

Max Activating Token Index: 182

Text #1

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.8630. Min Act: 0.0000

Data Index: 811815 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1584010 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7875. Min Act: -0.0000

Data Index: 307113 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7950. Min Act: -0.0000

Data Index: 1564446 (The Pile)

Max Activating Token Index: 898

Text #5

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7430. Min Act: -0.0000

Data Index: 857277 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7854. Min Act: -0.0000

Data Index: 744424 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1216452 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7388. Min Act: -0.0000

Data Index: 75317 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7591. Min Act: -0.0000

Data Index: 22579 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7607. Min Act: -0.0000

Data Index: 233765 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7467. Min Act: -0.0000

Data Index: 809271 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1389440 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6786. Min Act: -0.0000

Data Index: 1287838 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7019. Min Act: -0.0000

Data Index: 1129025 (The Pile)

Max Activating Token Index: 322

Text #15

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1049182 (The Pile)

Max Activating Token Index: 74

Text #16

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6943. Min Act: -0.0000

Data Index: 831289 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7314. Min Act: -0.0000

Data Index: 569393 (The Pile)

Max Activating Token Index: 386

Text #18

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1030298 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6849. Min Act: -0.0000

Data Index: 363048 (The Pile)

Max Activating Token Index: 201