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

Dataset: The Pile

Neuron 956 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: 0.2719. Min Range: -0.2719

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1619712 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2719. Min Act: -0.0000

Data Index: 24184 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2371. Min Act: -0.0000

Data Index: 853969 (The Pile)

Max Activating Token Index: 499

Text #3

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2132. Min Act: -0.0000

Data Index: 92873 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1246073 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2011. Min Act: -0.0000

Data Index: 447508 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1272503 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1861140 (The Pile)

Max Activating Token Index: 944

Text #8

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1911. Min Act: -0.0000

Data Index: 560616 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1982. Min Act: -0.0000

Data Index: 605313 (The Pile)

Max Activating Token Index: 794

Text #10

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1912. Min Act: -0.0000

Data Index: 758164 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1633997 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1147696 (The Pile)

Max Activating Token Index: 586

Text #13

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1310948 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2123. Min Act: -0.0000

Data Index: 896385 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1639. Min Act: -0.0000

Data Index: 259233 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1699. Min Act: -0.0000

Data Index: 193404 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1104269 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1481. Min Act: -0.0000

Data Index: 1472412 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1670. Min Act: -0.0000

Data Index: 456484 (The Pile)

Max Activating Token Index: 539