Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2975 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1868074 (The Pile)

Max Activating Token Index: 155

Text #1

Max Range: 1.2323. Min Range: -1.2323

Max Act: 1.0644. Min Act: -0.0000

Data Index: 956177 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.9824. Min Act: -0.0000

Data Index: 691609 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1900561 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8140. Min Act: -0.0000

Data Index: 50519 (The Pile)

Max Activating Token Index: 474

Text #5

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1276778 (The Pile)

Max Activating Token Index: 271

Text #6

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1911983 (The Pile)

Max Activating Token Index: 382

Text #7

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8626. Min Act: -0.0000

Data Index: 1060539 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1666637 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1095765 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.7547. Min Act: -0.0000

Data Index: 543575 (The Pile)

Max Activating Token Index: 241

Text #11

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8045. Min Act: -0.0000

Data Index: 112368 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1758770 (The Pile)

Max Activating Token Index: 330

Text #13

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1727707 (The Pile)

Max Activating Token Index: 719

Text #14

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8020. Min Act: -0.0000

Data Index: 1096406 (The Pile)

Max Activating Token Index: 273

Text #15

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.8173. Min Act: -0.0000

Data Index: 874361 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.7687. Min Act: -0.0000

Data Index: 194324 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1098575 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.7392. Min Act: -0.0000

Data Index: 799462 (The Pile)

Max Activating Token Index: 37

Text #19

Max Range: 1.2323. Min Range: -1.2323

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1146089 (The Pile)

Max Activating Token Index: 184