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

Dataset: The Pile

Neuron 889 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.9927. Min Act: -0.0000

Data Index: 271746 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.9704. Min Act: -0.0000

Data Index: 1106970 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.5822. Min Act: -0.0000

Data Index: 1879210 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.8344. Min Act: -0.0000

Data Index: 945238 (The Pile)

Max Activating Token Index: 799

Text #4

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.6974. Min Act: -0.0000

Data Index: 664352 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.5617. Min Act: -0.0000

Data Index: 740680 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.3580. Min Act: -0.0000

Data Index: 994200 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.3574. Min Act: -0.0000

Data Index: 391687 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.5245. Min Act: -0.0000

Data Index: 22394 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.3454. Min Act: -0.0000

Data Index: 1060823 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.5035. Min Act: -0.0000

Data Index: 191226 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.3075. Min Act: -0.0000

Data Index: 1559920 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.4825. Min Act: -0.0000

Data Index: 78681 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.4518. Min Act: -0.0000

Data Index: 1535642 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.4663. Min Act: -0.0000

Data Index: 1387716 (The Pile)

Max Activating Token Index: 1014

Text #15

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.4514. Min Act: -0.0000

Data Index: 138435 (The Pile)

Max Activating Token Index: 198

Text #16

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.4530. Min Act: -0.0000

Data Index: 697769 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.4496. Min Act: -0.0000

Data Index: 1681915 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.2806. Min Act: -0.0000

Data Index: 681806 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 3.9927. Min Range: -3.9927

Max Act: 3.3913. Min Act: -0.0000

Data Index: 1482023 (The Pile)

Max Activating Token Index: 842