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

Dataset: The Pile

Neuron 703 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1673992 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1306697 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.0254. Min Act: -0.0000

Data Index: 278858 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9316. Min Act: -0.0000

Data Index: 797089 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8474. Min Act: -0.0000

Data Index: 619960 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.2865. Min Act: -0.0000

Data Index: 1031840 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 1.2865. Min Range: -1.2865

Max Act: 1.0230. Min Act: -0.0000

Data Index: 490430 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8585. Min Act: -0.0000

Data Index: 831747 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1079951 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8783. Min Act: -0.0000

Data Index: 556395 (The Pile)

Max Activating Token Index: 628

Text #10

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7781. Min Act: -0.0000

Data Index: 1741168 (The Pile)

Max Activating Token Index: 674

Text #11

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1337290 (The Pile)

Max Activating Token Index: 233

Text #12

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1952768 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7662. Min Act: -0.0000

Data Index: 236104 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8112. Min Act: -0.0000

Data Index: 387404 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1388351 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.9156. Min Act: -0.0000

Data Index: 799439 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.7660. Min Act: -0.0000

Data Index: 1631939 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.6779. Min Act: -0.0000

Data Index: 193229 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 1.2865. Min Range: -1.2865

Max Act: 0.6457. Min Act: -0.0000

Data Index: 768793 (The Pile)

Max Activating Token Index: 532