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

Dataset: The Pile

Neuron 1887 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.8230. Min Act: -0.0000

Data Index: 885723 (The Pile)

Max Activating Token Index: 591

Text #1

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.6311. Min Act: -0.0000

Data Index: 1069227 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.7228. Min Act: -0.0000

Data Index: 1149574 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.4597. Min Act: -0.0000

Data Index: 1077255 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.8617. Min Act: -0.0000

Data Index: 1075922 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.0196. Min Act: -0.0000

Data Index: 492152 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.1769. Min Act: -0.0000

Data Index: 1854167 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.8094. Min Act: -0.0000

Data Index: 1612794 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.5882. Min Act: -0.0000

Data Index: 1665650 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.3740. Min Act: -0.0000

Data Index: 1815639 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.1042. Min Act: -0.0000

Data Index: 68029 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.0653. Min Act: -0.0000

Data Index: 213139 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.0270. Min Act: -0.0000

Data Index: 1414015 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.4773. Min Act: -0.0000

Data Index: 942467 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.0101. Min Act: -0.0000

Data Index: 292782 (The Pile)

Max Activating Token Index: 427

Text #15

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.3816. Min Act: -0.0000

Data Index: 646102 (The Pile)

Max Activating Token Index: 677

Text #16

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.9305. Min Act: -0.0000

Data Index: 148503 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.7517. Min Act: -0.0000

Data Index: 45970 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 6.8230. Min Range: -6.8230

Max Act: 5.6731. Min Act: -0.0000

Data Index: 755646 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 6.8230. Min Range: -6.8230

Max Act: 6.2066. Min Act: -0.0000

Data Index: 415825 (The Pile)

Max Activating Token Index: 221