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

Dataset: The Pile

Neuron 2807 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: 1.0803. Min Range: -1.0803

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1700602 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9799. Min Act: -0.0000

Data Index: 282863 (The Pile)

Max Activating Token Index: 902

Text #2

Max Range: 1.0803. Min Range: -1.0803

Max Act: 1.0086. Min Act: -0.0000

Data Index: 577972 (The Pile)

Max Activating Token Index: 540

Text #3

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9893. Min Act: -0.0000

Data Index: 433169 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 1.0803. Min Range: -1.0803

Max Act: 1.0230. Min Act: -0.0000

Data Index: 1855331 (The Pile)

Max Activating Token Index: 801

Text #5

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1665236 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.8984. Min Act: -0.0000

Data Index: 504071 (The Pile)

Max Activating Token Index: 701

Text #7

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9935. Min Act: -0.0000

Data Index: 698499 (The Pile)

Max Activating Token Index: 270

Text #8

Max Range: 1.0803. Min Range: -1.0803

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1741423 (The Pile)

Max Activating Token Index: 821

Text #9

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9766. Min Act: -0.0000

Data Index: 6465 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1629911 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1028171 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 1.0803. Min Range: -1.0803

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1784762 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 1.0803. Min Range: -1.0803

Max Act: 1.0803. Min Act: -0.0000

Data Index: 1246350 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9539. Min Act: -0.0000

Data Index: 604755 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1408717 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9752. Min Act: -0.0000

Data Index: 836631 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1463509 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1038142 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 1.0803. Min Range: -1.0803

Max Act: 0.9117. Min Act: -0.0000

Data Index: 991645 (The Pile)

Max Activating Token Index: 503