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

Dataset: The Pile

Neuron 4454 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.8569. Min Act: -0.0000

Data Index: 606404 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.7056. Min Act: -0.0000

Data Index: 786241 (The Pile)

Max Activating Token Index: 996

Text #2

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.4999. Min Act: -0.0000

Data Index: 91354 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1300525 (The Pile)

Max Activating Token Index: 8

Text #4

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.1025. Min Act: -0.0000

Data Index: 622871 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.1115. Min Act: 0.0000

Data Index: 542689 (The Pile)

Max Activating Token Index: 788

Text #6

Max Range: 1.8569. Min Range: -1.8569

Max Act: 1.0474. Min Act: -0.0000

Data Index: 981553 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.8828. Min Act: -0.0000

Data Index: 780996 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1511496 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.8610. Min Act: -0.0000

Data Index: 113259 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1083793 (The Pile)

Max Activating Token Index: 215

Text #11

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.7510. Min Act: -0.0000

Data Index: 616036 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1700296 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1346255 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1341653 (The Pile)

Max Activating Token Index: 593

Text #15

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.7588. Min Act: -0.0000

Data Index: 246673 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.8616. Min Act: -0.0000

Data Index: 965482 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.6878. Min Act: 0.0000

Data Index: 1639699 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1615445 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.8569. Min Range: -1.8569

Max Act: 0.7114. Min Act: -0.0000

Data Index: 577471 (The Pile)

Max Activating Token Index: 811