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

Dataset: The Pile

Neuron 4644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9752. Min Range: -5.9752

Max Act: 5.9752. Min Act: -0.0000

Data Index: 336486 (The Pile)

Max Activating Token Index: 830

Text #1

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.5731. Min Act: -0.0000

Data Index: 129244 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.8603. Min Act: -0.0000

Data Index: 1766818 (The Pile)

Max Activating Token Index: 253

Text #3

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.5119. Min Act: -0.0000

Data Index: 157668 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.7442. Min Act: -0.0000

Data Index: 998689 (The Pile)

Max Activating Token Index: 67

Text #5

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.6903. Min Act: -0.0000

Data Index: 1915374 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.2712. Min Act: -0.0000

Data Index: 1697687 (The Pile)

Max Activating Token Index: 527

Text #7

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.3078. Min Act: -0.0000

Data Index: 491682 (The Pile)

Max Activating Token Index: 712

Text #8

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.1960. Min Act: -0.0000

Data Index: 717672 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 5.9752. Min Range: -5.9752

Max Act: 3.8365. Min Act: -0.0000

Data Index: 1264712 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.1498. Min Act: -0.0000

Data Index: 160462 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.3323. Min Act: -0.0000

Data Index: 785872 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.1086. Min Act: -0.0000

Data Index: 874998 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 5.9752. Min Range: -5.9752

Max Act: 3.8502. Min Act: -0.0000

Data Index: 773197 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.0418. Min Act: -0.0000

Data Index: 846399 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 5.9752. Min Range: -5.9752

Max Act: 4.1582. Min Act: -0.0000

Data Index: 661120 (The Pile)

Max Activating Token Index: 106

Text #16

Max Range: 5.9752. Min Range: -5.9752

Max Act: 3.6064. Min Act: -0.0000

Data Index: 1758722 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 5.9752. Min Range: -5.9752

Max Act: 2.8178. Min Act: -0.0000

Data Index: 1285565 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 5.9752. Min Range: -5.9752

Max Act: 3.8487. Min Act: -0.0000

Data Index: 1146725 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 5.9752. Min Range: -5.9752

Max Act: 3.6486. Min Act: -0.0000

Data Index: 847923 (The Pile)

Max Activating Token Index: 665