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

Dataset: The Pile

Neuron 4164 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: 0.9126. Min Range: -0.9126

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1926459 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1293370 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8607. Min Act: -0.0000

Data Index: 75733 (The Pile)

Max Activating Token Index: 414

Text #3

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8664. Min Act: -0.0000

Data Index: 473900 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8625. Min Act: -0.0000

Data Index: 585086 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1604904 (The Pile)

Max Activating Token Index: 579

Text #6

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8646. Min Act: -0.0000

Data Index: 149737 (The Pile)

Max Activating Token Index: 243

Text #7

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7809. Min Act: -0.0000

Data Index: 945319 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8003. Min Act: -0.0000

Data Index: 721092 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8877. Min Act: -0.0000

Data Index: 877176 (The Pile)

Max Activating Token Index: 266

Text #10

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1349001 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6655. Min Act: -0.0000

Data Index: 263623 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1124330 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8613. Min Act: -0.0000

Data Index: 29255 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7997. Min Act: -0.0000

Data Index: 634456 (The Pile)

Max Activating Token Index: 783

Text #15

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1014938 (The Pile)

Max Activating Token Index: 836

Text #16

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7835. Min Act: -0.0000

Data Index: 603535 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1562543 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1227484 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.9126. Min Range: -0.9126

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1062354 (The Pile)

Max Activating Token Index: 432