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

Dataset: The Pile

Neuron 4406 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.8824. Min Act: -0.0000

Data Index: 879512 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.8388. Min Act: -0.0000

Data Index: 219202 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7367. Min Act: -0.0000

Data Index: 1287735 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5504. Min Act: -0.0000

Data Index: 682091 (The Pile)

Max Activating Token Index: 876

Text #4

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7462. Min Act: -0.0000

Data Index: 1275787 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6242. Min Act: -0.0000

Data Index: 182598 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6917. Min Act: -0.0000

Data Index: 863751 (The Pile)

Max Activating Token Index: 946

Text #7

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6918. Min Act: -0.0000

Data Index: 1844692 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5683. Min Act: -0.0000

Data Index: 609026 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1226230 (The Pile)

Max Activating Token Index: 360

Text #10

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7689. Min Act: -0.0000

Data Index: 1155238 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5019. Min Act: -0.0000

Data Index: 595810 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4149. Min Act: -0.0000

Data Index: 373353 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4979. Min Act: -0.0000

Data Index: 48968 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7748. Min Act: -0.0000

Data Index: 896863 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5841. Min Act: -0.0000

Data Index: 599049 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4974. Min Act: -0.0000

Data Index: 1840341 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5043. Min Act: -0.0000

Data Index: 798706 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1370998 (The Pile)

Max Activating Token Index: 434

Text #19

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4765. Min Act: -0.0000

Data Index: 776695 (The Pile)

Max Activating Token Index: 865