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

Dataset: The Pile

Neuron 4939 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: 5.4081. Min Range: -5.4081

Max Act: 5.4081. Min Act: -0.0000

Data Index: 1207445 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 5.4081. Min Range: -5.4081

Max Act: 5.2768. Min Act: -0.0000

Data Index: 6213 (The Pile)

Max Activating Token Index: 614

Text #2

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.9646. Min Act: -0.0000

Data Index: 45357 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 5.4081. Min Range: -5.4081

Max Act: 5.1468. Min Act: -0.0000

Data Index: 1324289 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.7257. Min Act: -0.0000

Data Index: 1991629 (The Pile)

Max Activating Token Index: 641

Text #5

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.9164. Min Act: -0.0000

Data Index: 1898881 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.5913. Min Act: -0.0000

Data Index: 991267 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6827. Min Act: -0.0000

Data Index: 1857734 (The Pile)

Max Activating Token Index: 49

Text #8

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6193. Min Act: -0.0000

Data Index: 252808 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6718. Min Act: -0.0000

Data Index: 1506977 (The Pile)

Max Activating Token Index: 72

Text #10

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.9491. Min Act: -0.0000

Data Index: 849107 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6124. Min Act: -0.0000

Data Index: 425508 (The Pile)

Max Activating Token Index: 199

Text #12

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.5672. Min Act: -0.0000

Data Index: 897705 (The Pile)

Max Activating Token Index: 895

Text #13

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.2345. Min Act: -0.0000

Data Index: 540579 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6542. Min Act: -0.0000

Data Index: 229669 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6477. Min Act: -0.0000

Data Index: 214112 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.6268. Min Act: -0.0000

Data Index: 1374566 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.3836. Min Act: -0.0000

Data Index: 1077393 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.2867. Min Act: -0.0000

Data Index: 807400 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 5.4081. Min Range: -5.4081

Max Act: 4.3284. Min Act: -0.0000

Data Index: 1811988 (The Pile)

Max Activating Token Index: 132