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

Dataset: The Pile

Neuron 4741 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: 1.9674. Min Range: -1.9674

Max Act: 1.8518. Min Act: -0.0000

Data Index: 131785 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.9674. Min Act: -0.0000

Data Index: 959480 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.5004. Min Act: -0.0000

Data Index: 1338411 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.3705. Min Act: -0.0000

Data Index: 1616225 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.3955. Min Act: -0.0000

Data Index: 323045 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.3274. Min Act: -0.0000

Data Index: 555850 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.3233. Min Act: -0.0000

Data Index: 216312 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1211910 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1274371 (The Pile)

Max Activating Token Index: 318

Text #9

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.2339. Min Act: -0.0000

Data Index: 1960937 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.1617. Min Act: -0.0000

Data Index: 417760 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.2191. Min Act: -0.0000

Data Index: 22795 (The Pile)

Max Activating Token Index: 856

Text #12

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.2006. Min Act: -0.0000

Data Index: 289233 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1694330 (The Pile)

Max Activating Token Index: 701

Text #14

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1225082 (The Pile)

Max Activating Token Index: 740

Text #15

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.1818. Min Act: -0.0000

Data Index: 1998153 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.2571. Min Act: -0.0000

Data Index: 62976 (The Pile)

Max Activating Token Index: 437

Text #17

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1669190 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.1783. Min Act: -0.0000

Data Index: 1855168 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 1.9674. Min Range: -1.9674

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1242571 (The Pile)

Max Activating Token Index: 559