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

Dataset: The Pile

Neuron 1606 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.6858. Min Act: -0.0000

Data Index: 1142046 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.9824. Min Act: -0.0000

Data Index: 1862359 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.4627. Min Act: -0.0000

Data Index: 504941 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.4324. Min Act: -0.0000

Data Index: 207868 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.3420. Min Act: -0.0000

Data Index: 324288 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.0824. Min Act: -0.0000

Data Index: 1600381 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.1581. Min Act: -0.0000

Data Index: 1402753 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.4217. Min Act: -0.0000

Data Index: 183943 (The Pile)

Max Activating Token Index: 245

Text #8

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.7701. Min Act: -0.0000

Data Index: 1855988 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.3683. Min Act: -0.0000

Data Index: 1800167 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.0571. Min Act: -0.0000

Data Index: 254918 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.8264. Min Act: -0.0000

Data Index: 1035160 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.8532. Min Act: -0.0000

Data Index: 1407819 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.4324. Min Act: -0.0000

Data Index: 611053 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.0037. Min Act: -0.0000

Data Index: 133523 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.6105. Min Act: -0.0000

Data Index: 1215017 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.5823. Min Act: -0.0000

Data Index: 1005139 (The Pile)

Max Activating Token Index: 165

Text #17

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.3721. Min Act: -0.0000

Data Index: 386718 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 7.9824. Min Range: -7.9824

Max Act: 6.7496. Min Act: -0.0000

Data Index: 1567007 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 7.9824. Min Range: -7.9824

Max Act: 7.0701. Min Act: -0.0000

Data Index: 384812 (The Pile)

Max Activating Token Index: 141