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

Dataset: The Pile

Neuron 3194 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: 0.1215. Min Range: -0.1215

Max Act: 0.1215. Min Act: -0.0000

Data Index: 241501 (The Pile)

Max Activating Token Index: 642

Text #1

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1402238 (The Pile)

Max Activating Token Index: 767

Text #2

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0966. Min Act: -0.0000

Data Index: 708835 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1778955 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1572988 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1660347 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0928. Min Act: -0.0000

Data Index: 299525 (The Pile)

Max Activating Token Index: 578

Text #7

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0930. Min Act: -0.0000

Data Index: 993039 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1760899 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0894. Min Act: -0.0000

Data Index: 185436 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0871. Min Act: -0.0000

Data Index: 957714 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0863. Min Act: -0.0000

Data Index: 312223 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0889. Min Act: -0.0000

Data Index: 957557 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0914. Min Act: -0.0000

Data Index: 668105 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0849. Min Act: -0.0000

Data Index: 702462 (The Pile)

Max Activating Token Index: 929

Text #15

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0866. Min Act: -0.0000

Data Index: 557869 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1659836 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0848. Min Act: -0.0000

Data Index: 1301383 (The Pile)

Max Activating Token Index: 724

Text #18

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0791. Min Act: -0.0000

Data Index: 559972 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 0.1215. Min Range: -0.1215

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1068083 (The Pile)

Max Activating Token Index: 461