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

Dataset: The Pile

Neuron 2072 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1521364 (The Pile)

Max Activating Token Index: 294

Text #1

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.2363. Min Act: -0.0000

Data Index: 1070587 (The Pile)

Max Activating Token Index: 601

Text #2

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.2148. Min Act: -0.0000

Data Index: 17670 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.2162. Min Act: -0.0000

Data Index: 1865266 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.1187. Min Act: -0.0000

Data Index: 533193 (The Pile)

Max Activating Token Index: 566

Text #5

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.1430. Min Act: -0.0000

Data Index: 680380 (The Pile)

Max Activating Token Index: 211

Text #6

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.1095. Min Act: -0.0000

Data Index: 20918 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.1199. Min Act: -0.0000

Data Index: 217504 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1485253 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0771. Min Act: -0.0000

Data Index: 1322129 (The Pile)

Max Activating Token Index: 531

Text #10

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0717. Min Act: -0.0000

Data Index: 1700534 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1710710 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0959. Min Act: -0.0000

Data Index: 1869910 (The Pile)

Max Activating Token Index: 318

Text #13

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0595. Min Act: -0.0000

Data Index: 1759347 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1944204 (The Pile)

Max Activating Token Index: 723

Text #15

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1129372 (The Pile)

Max Activating Token Index: 296

Text #16

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0567. Min Act: -0.0000

Data Index: 612713 (The Pile)

Max Activating Token Index: 190

Text #17

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0588. Min Act: -0.0000

Data Index: 634647 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 1.4962. Min Range: -1.4962

Max Act: 0.9880. Min Act: -0.0000

Data Index: 121516 (The Pile)

Max Activating Token Index: 1007

Text #19

Max Range: 1.4962. Min Range: -1.4962

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1332783 (The Pile)

Max Activating Token Index: 519