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

Dataset: The Pile

Neuron 1723 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.7683. Min Act: -0.0000

Data Index: 933717 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1778440 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6247. Min Act: -0.0000

Data Index: 631785 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6061. Min Act: -0.0000

Data Index: 111520 (The Pile)

Max Activating Token Index: 874

Text #4

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1942912 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5824. Min Act: -0.0000

Data Index: 973149 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5671. Min Act: -0.0000

Data Index: 683249 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5312. Min Act: -0.0000

Data Index: 475173 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5421. Min Act: -0.0000

Data Index: 480107 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1338710 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1717058 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1924115 (The Pile)

Max Activating Token Index: 549

Text #12

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1866527 (The Pile)

Max Activating Token Index: 699

Text #13

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5045. Min Act: -0.0000

Data Index: 162570 (The Pile)

Max Activating Token Index: 236

Text #14

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1052490 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1695008 (The Pile)

Max Activating Token Index: 815

Text #16

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1089674 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.4522. Min Act: -0.0000

Data Index: 266049 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1680914 (The Pile)

Max Activating Token Index: 740

Text #19

Max Range: 0.7683. Min Range: -0.7683

Max Act: 0.4798. Min Act: -0.0000

Data Index: 199408 (The Pile)

Max Activating Token Index: 539