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

Dataset: The Pile

Neuron 1096 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.9253. Min Act: -0.0000

Data Index: 661594 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.9858. Min Act: -0.0000

Data Index: 1935155 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.6394. Min Act: -0.0000

Data Index: 1517916 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.9675. Min Act: -0.0000

Data Index: 679626 (The Pile)

Max Activating Token Index: 938

Text #4

Max Range: 3.9858. Min Range: -3.9858

Max Act: 3.1271. Min Act: -0.0000

Data Index: 1480037 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.7614. Min Act: -0.0000

Data Index: 1166035 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.8662. Min Act: -0.0000

Data Index: 536983 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.8460. Min Act: -0.0000

Data Index: 347870 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.8125. Min Act: -0.0000

Data Index: 94574 (The Pile)

Max Activating Token Index: 932

Text #9

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.6220. Min Act: -0.0000

Data Index: 953759 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.3864. Min Act: -0.0000

Data Index: 1680920 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.5534. Min Act: -0.0000

Data Index: 1733391 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.5771. Min Act: -0.0000

Data Index: 1726421 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.8070. Min Act: -0.0000

Data Index: 1834915 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.6437. Min Act: -0.0000

Data Index: 1608994 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.6530. Min Act: -0.0000

Data Index: 992991 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.5058. Min Act: -0.0000

Data Index: 167002 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.7014. Min Act: -0.0000

Data Index: 264723 (The Pile)

Max Activating Token Index: 978

Text #18

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.5703. Min Act: -0.0000

Data Index: 1309650 (The Pile)

Max Activating Token Index: 534

Text #19

Max Range: 3.9858. Min Range: -3.9858

Max Act: 2.5616. Min Act: -0.0000

Data Index: 1297025 (The Pile)

Max Activating Token Index: 12