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

Dataset: The Pile

Neuron 1175 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.6517. Min Act: -0.0000

Data Index: 1633344 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.5486. Min Act: -0.0000

Data Index: 1727364 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.0838. Min Act: -0.0000

Data Index: 548016 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.4226. Min Act: -0.0000

Data Index: 1892658 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 3.6517. Min Range: -3.6517

Max Act: 3.2778. Min Act: -0.0000

Data Index: 619033 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.9499. Min Act: -0.0000

Data Index: 992385 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.4370. Min Act: -0.0000

Data Index: 1709988 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.5076. Min Act: 0.0000

Data Index: 1263174 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.3895. Min Act: -0.0000

Data Index: 1867394 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.4356. Min Act: -0.0000

Data Index: 86713 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.0774. Min Act: -0.0000

Data Index: 1820666 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 3.6517. Min Range: -3.6517

Max Act: 1.8219. Min Act: -0.0000

Data Index: 813132 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 3.6517. Min Range: -3.6517

Max Act: 1.8218. Min Act: -0.0000

Data Index: 1317330 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.0313. Min Act: -0.0000

Data Index: 1594369 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.0328. Min Act: -0.0000

Data Index: 419769 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.3317. Min Act: 0.0000

Data Index: 683337 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 3.6517. Min Range: -3.6517

Max Act: 1.9293. Min Act: 0.0000

Data Index: 1093123 (The Pile)

Max Activating Token Index: 825

Text #17

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.1860. Min Act: -0.0000

Data Index: 1921040 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.1314. Min Act: 0.0000

Data Index: 1352796 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 3.6517. Min Range: -3.6517

Max Act: 2.2087. Min Act: -0.0000

Data Index: 404435 (The Pile)

Max Activating Token Index: 191