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

Dataset: The Pile

Neuron 4758 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: 1.0233. Min Range: -1.0233

Max Act: 1.0233. Min Act: -0.0000

Data Index: 754363 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1608597 (The Pile)

Max Activating Token Index: 90

Text #2

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.8438. Min Act: -0.0000

Data Index: 809807 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1665135 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1545638 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.6516. Min Act: -0.0000

Data Index: 826436 (The Pile)

Max Activating Token Index: 414

Text #6

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1712228 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1035614 (The Pile)

Max Activating Token Index: 549

Text #8

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.6251. Min Act: -0.0000

Data Index: 215463 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.6031. Min Act: -0.0000

Data Index: 431507 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1097409 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1277506 (The Pile)

Max Activating Token Index: 675

Text #12

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.6131. Min Act: -0.0000

Data Index: 655608 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1207162 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1329862 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1257716 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1404520 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.5728. Min Act: -0.0000

Data Index: 999987 (The Pile)

Max Activating Token Index: 350

Text #18

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.5791. Min Act: -0.0000

Data Index: 726275 (The Pile)

Max Activating Token Index: 75

Text #19

Max Range: 1.0233. Min Range: -1.0233

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1255772 (The Pile)

Max Activating Token Index: 113