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

Dataset: The Pile

Neuron 4725 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9412. Min Act: -0.0000

Data Index: 687732 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 1.0151. Min Range: -1.0151

Max Act: 1.0151. Min Act: -0.0000

Data Index: 998775 (The Pile)

Max Activating Token Index: 781

Text #2

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9900. Min Act: -0.0000

Data Index: 1639762 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1876443 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9100. Min Act: -0.0000

Data Index: 1743261 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9128. Min Act: -0.0000

Data Index: 1819586 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1839161 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9507. Min Act: -0.0000

Data Index: 1528545 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1995462 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1614050 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1340516 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1377547 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.9148. Min Act: -0.0000

Data Index: 151832 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1084672 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1148966 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8342. Min Act: -0.0000

Data Index: 514604 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1378966 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8089. Min Act: -0.0000

Data Index: 484389 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1732601 (The Pile)

Max Activating Token Index: 504

Text #19

Max Range: 1.0151. Min Range: -1.0151

Max Act: 0.7967. Min Act: -0.0000

Data Index: 680158 (The Pile)

Max Activating Token Index: 506