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

Dataset: The Pile

Neuron 1935 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5577. Min Range: -1.5577

Max Act: 1.5577. Min Act: -0.0000

Data Index: 1454867 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 1.5577. Min Range: -1.5577

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1674833 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 1.5577. Min Range: -1.5577

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1950587 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.5577. Min Range: -1.5577

Max Act: 1.0424. Min Act: -0.0000

Data Index: 1006809 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9534. Min Act: -0.0000

Data Index: 591334 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1467551 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 1.5577. Min Range: -1.5577

Max Act: 1.0188. Min Act: -0.0000

Data Index: 613348 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9445. Min Act: -0.0000

Data Index: 1134951 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9767. Min Act: -0.0000

Data Index: 822746 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9356. Min Act: -0.0000

Data Index: 1438466 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1670077 (The Pile)

Max Activating Token Index: 201

Text #11

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1873903 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9520. Min Act: -0.0001

Data Index: 17649 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1005976 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9760. Min Act: -0.0000

Data Index: 948125 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9462. Min Act: -0.0000

Data Index: 386261 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9183. Min Act: -0.0000

Data Index: 462352 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1198239 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1203763 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 1.5577. Min Range: -1.5577

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1817168 (The Pile)

Max Activating Token Index: 923