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

Dataset: The Pile

Neuron 2197 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: 1.8824. Min Range: -1.8824

Max Act: 1.8824. Min Act: -0.0000

Data Index: 1817768 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7531. Min Act: -0.0000

Data Index: 1290810 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7154. Min Act: -0.0000

Data Index: 1277390 (The Pile)

Max Activating Token Index: 407

Text #3

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6629. Min Act: -0.0000

Data Index: 1515581 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.7110. Min Act: -0.0000

Data Index: 1953699 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4996. Min Act: -0.0000

Data Index: 99486 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.6542. Min Act: -0.0000

Data Index: 942422 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.4435. Min Act: -0.0000

Data Index: 236049 (The Pile)

Max Activating Token Index: 228

Text #8

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.5120. Min Act: -0.0000

Data Index: 1182710 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2932. Min Act: -0.0000

Data Index: 557077 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1724488 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2485. Min Act: -0.0000

Data Index: 742199 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1439778 (The Pile)

Max Activating Token Index: 200

Text #13

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2905. Min Act: -0.0000

Data Index: 272141 (The Pile)

Max Activating Token Index: 825

Text #14

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1026817 (The Pile)

Max Activating Token Index: 229

Text #15

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2751. Min Act: -0.0000

Data Index: 301324 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2825. Min Act: -0.0000

Data Index: 1036515 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2692. Min Act: -0.0000

Data Index: 643878 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2616. Min Act: -0.0000

Data Index: 1402228 (The Pile)

Max Activating Token Index: 21

Text #19

Max Range: 1.8824. Min Range: -1.8824

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1569697 (The Pile)

Max Activating Token Index: 37