Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2521 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.0219. Min Range: -3.0219

Max Act: 3.0219. Min Act: -0.0000

Data Index: 411660 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 3.0219. Min Range: -3.0219

Max Act: 2.4059. Min Act: -0.0000

Data Index: 1605088 (The Pile)

Max Activating Token Index: 813

Text #2

Max Range: 3.0219. Min Range: -3.0219

Max Act: 2.4848. Min Act: -0.0001

Data Index: 347785 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.9803. Min Act: -0.0000

Data Index: 148439 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.8173. Min Act: -0.0000

Data Index: 1083742 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.8230. Min Act: -0.0000

Data Index: 609547 (The Pile)

Max Activating Token Index: 329

Text #6

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.7421. Min Act: -0.0000

Data Index: 1729782 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.8263. Min Act: -0.0000

Data Index: 246587 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.6342. Min Act: -0.0000

Data Index: 200782 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.7188. Min Act: -0.0000

Data Index: 1224390 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.5606. Min Act: -0.0000

Data Index: 643079 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.4883. Min Act: -0.0000

Data Index: 952012 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.5398. Min Act: -0.0000

Data Index: 814755 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.5308. Min Act: -0.0000

Data Index: 727159 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.5696. Min Act: -0.0000

Data Index: 71413 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1422607 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.6551. Min Act: -0.0000

Data Index: 1175298 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.6298. Min Act: -0.0000

Data Index: 1570057 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.5907. Min Act: -0.0000

Data Index: 1431298 (The Pile)

Max Activating Token Index: 261

Text #19

Max Range: 3.0219. Min Range: -3.0219

Max Act: 1.5996. Min Act: -0.0000

Data Index: 1884991 (The Pile)

Max Activating Token Index: 198