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

Dataset: The Pile

Neuron 3828 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: 0.8096. Min Range: -0.8096

Max Act: 0.8096. Min Act: -0.0000

Data Index: 40548 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1422165 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1246459 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5867. Min Act: -0.0000

Data Index: 1554581 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6293. Min Act: -0.0000

Data Index: 1594253 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6005. Min Act: -0.0000

Data Index: 519872 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1031577 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1124054 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.6057. Min Act: -0.0000

Data Index: 82634 (The Pile)

Max Activating Token Index: 331

Text #9

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5577. Min Act: -0.0000

Data Index: 279699 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5159. Min Act: -0.0000

Data Index: 853851 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1148688 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1673592 (The Pile)

Max Activating Token Index: 273

Text #13

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1010523 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5194. Min Act: -0.0000

Data Index: 396106 (The Pile)

Max Activating Token Index: 593

Text #15

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5122. Min Act: -0.0000

Data Index: 57533 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5617. Min Act: -0.0000

Data Index: 820251 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5915. Min Act: -0.0000

Data Index: 737576 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1194951 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.8096. Min Range: -0.8096

Max Act: 0.5058. Min Act: -0.0000

Data Index: 552962 (The Pile)

Max Activating Token Index: 28