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

Dataset: The Pile

Neuron 255 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: 0.6562. Min Range: -0.6562

Max Act: 0.6562. Min Act: -0.0000

Data Index: 94978 (The Pile)

Max Activating Token Index: 534

Text #1

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6472. Min Act: -0.0000

Data Index: 1101804 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6465. Min Act: -0.0000

Data Index: 608016 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1593070 (The Pile)

Max Activating Token Index: 464

Text #4

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1324290 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6253. Min Act: -0.0000

Data Index: 1474905 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1718010 (The Pile)

Max Activating Token Index: 548

Text #7

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5691. Min Act: -0.0000

Data Index: 427637 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6121. Min Act: -0.0000

Data Index: 1756492 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1390215 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6066. Min Act: -0.0000

Data Index: 327314 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1813296 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1140238 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1406786 (The Pile)

Max Activating Token Index: 313

Text #14

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5753. Min Act: -0.0000

Data Index: 922199 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1614787 (The Pile)

Max Activating Token Index: 799

Text #16

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5927. Min Act: -0.0000

Data Index: 595524 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5504. Min Act: -0.0000

Data Index: 92887 (The Pile)

Max Activating Token Index: 1021

Text #18

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1552421 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5833. Min Act: -0.0000

Data Index: 413563 (The Pile)

Max Activating Token Index: 574