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

Dataset: The Pile

Neuron 4204 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0331. Min Range: -1.0331

Max Act: 1.0281. Min Act: -0.0000

Data Index: 1491725 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 1.0331. Min Range: -1.0331

Max Act: 1.0331. Min Act: -0.0000

Data Index: 14768 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.9935. Min Act: -0.0000

Data Index: 1688924 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.9578. Min Act: 0.0000

Data Index: 439339 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 1.0331. Min Range: -1.0331

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1953777 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1164861 (The Pile)

Max Activating Token Index: 715

Text #6

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8752. Min Act: -0.0000

Data Index: 243101 (The Pile)

Max Activating Token Index: 588

Text #7

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1967430 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7515. Min Act: -0.0000

Data Index: 820976 (The Pile)

Max Activating Token Index: 357

Text #9

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1396504 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7285. Min Act: -0.0000

Data Index: 776053 (The Pile)

Max Activating Token Index: 970

Text #11

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.7050. Min Act: -0.0000

Data Index: 17325 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1191831 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.6897. Min Act: -0.0000

Data Index: 142789 (The Pile)

Max Activating Token Index: 701

Text #14

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.6655. Min Act: -0.0000

Data Index: 328160 (The Pile)

Max Activating Token Index: 461

Text #15

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1653863 (The Pile)

Max Activating Token Index: 844

Text #16

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1084011 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1421367 (The Pile)

Max Activating Token Index: 76

Text #18

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1915101 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 1.0331. Min Range: -1.0331

Max Act: 0.5377. Min Act: -0.0000

Data Index: 679038 (The Pile)

Max Activating Token Index: 124