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

Dataset: The Pile

Neuron 3035 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: 1.9801. Min Range: -1.9801

Max Act: 1.9475. Min Act: -0.0000

Data Index: 76497 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.9801. Min Act: -0.0000

Data Index: 1249422 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.8426. Min Act: -0.0000

Data Index: 1625906 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.9098. Min Act: -0.0000

Data Index: 1431858 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.8169. Min Act: -0.0000

Data Index: 1707473 (The Pile)

Max Activating Token Index: 579

Text #5

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.8051. Min Act: -0.0000

Data Index: 1418440 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.7708. Min Act: -0.0000

Data Index: 344776 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.6672. Min Act: -0.0000

Data Index: 650652 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.7384. Min Act: -0.0000

Data Index: 127614 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.6081. Min Act: -0.0000

Data Index: 601846 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.7074. Min Act: -0.0000

Data Index: 1436958 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.7056. Min Act: -0.0000

Data Index: 788558 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.7021. Min Act: -0.0000

Data Index: 156829 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.5882. Min Act: -0.0000

Data Index: 636629 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.7024. Min Act: -0.0000

Data Index: 416501 (The Pile)

Max Activating Token Index: 852

Text #15

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.6682. Min Act: -0.0000

Data Index: 1440615 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.6621. Min Act: -0.0000

Data Index: 278454 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.6563. Min Act: -0.0000

Data Index: 355297 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.6490. Min Act: -0.0000

Data Index: 641899 (The Pile)

Max Activating Token Index: 422

Text #19

Max Range: 1.9801. Min Range: -1.9801

Max Act: 1.7341. Min Act: -0.0000

Data Index: 356117 (The Pile)

Max Activating Token Index: 403