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

Dataset: The Pile

Neuron 2025 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5169. Min Act: -0.0000

Data Index: 430015 (The Pile)

Max Activating Token Index: 590

Text #1

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5063. Min Act: -0.0000

Data Index: 935104 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1296300 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4491. Min Act: -0.0000

Data Index: 175109 (The Pile)

Max Activating Token Index: 43

Text #4

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4218. Min Act: -0.0000

Data Index: 330692 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4169. Min Act: -0.0000

Data Index: 434559 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1544053 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1737143 (The Pile)

Max Activating Token Index: 803

Text #8

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3918. Min Act: -0.0000

Data Index: 379931 (The Pile)

Max Activating Token Index: 388

Text #9

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3985. Min Act: -0.0000

Data Index: 93945 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3876. Min Act: -0.0000

Data Index: 269722 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3902. Min Act: -0.0000

Data Index: 991469 (The Pile)

Max Activating Token Index: 897

Text #12

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1103151 (The Pile)

Max Activating Token Index: 948

Text #13

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1739574 (The Pile)

Max Activating Token Index: 608

Text #14

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3867. Min Act: -0.0000

Data Index: 958339 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1442130 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1563165 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1933263 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3725. Min Act: -0.0000

Data Index: 876612 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3745. Min Act: -0.0000

Data Index: 609839 (The Pile)

Max Activating Token Index: 165