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

Dataset: The Pile

Neuron 1972 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: 0.6009. Min Range: -0.6009

Max Act: 0.5230. Min Act: -0.0000

Data Index: 494678 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1322631 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1931361 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5260. Min Act: -0.0000

Data Index: 80137 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1799056 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1989573 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1360356 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5029. Min Act: -0.0000

Data Index: 755730 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4558. Min Act: -0.0000

Data Index: 588365 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5033. Min Act: -0.0000

Data Index: 340227 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1547578 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4690. Min Act: -0.0000

Data Index: 522127 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1672789 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1157931 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4685. Min Act: -0.0000

Data Index: 706546 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1823050 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4555. Min Act: -0.0000

Data Index: 113689 (The Pile)

Max Activating Token Index: 473

Text #17

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4724. Min Act: -0.0000

Data Index: 739117 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4346. Min Act: -0.0000

Data Index: 470284 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 0.6009. Min Range: -0.6009

Max Act: 0.4657. Min Act: -0.0000

Data Index: 275371 (The Pile)

Max Activating Token Index: 386