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

Dataset: The Pile

Neuron 264 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: 1.1093. Min Range: -1.1093

Max Act: 1.1093. Min Act: -0.0000

Data Index: 906191 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 1.1093. Min Range: -1.1093

Max Act: 1.0569. Min Act: 0.0000

Data Index: 789847 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.1093. Min Range: -1.1093

Max Act: 1.0276. Min Act: 0.0000

Data Index: 1003612 (The Pile)

Max Activating Token Index: 642

Text #3

Max Range: 1.1093. Min Range: -1.1093

Max Act: 1.0044. Min Act: -0.0000

Data Index: 192696 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1920157 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1601770 (The Pile)

Max Activating Token Index: 889

Text #6

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1797202 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7285. Min Act: -0.0000

Data Index: 1040734 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7065. Min Act: -0.0000

Data Index: 317775 (The Pile)

Max Activating Token Index: 834

Text #9

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1938829 (The Pile)

Max Activating Token Index: 931

Text #10

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.6741. Min Act: -0.0000

Data Index: 1702261 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7694. Min Act: -0.0000

Data Index: 1816168 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7187. Min Act: -0.0000

Data Index: 264798 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7251. Min Act: 0.0000

Data Index: 852949 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1888558 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1584595 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1209174 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1554686 (The Pile)

Max Activating Token Index: 175

Text #18

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.6903. Min Act: -0.0000

Data Index: 737743 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.6776. Min Act: 0.0000

Data Index: 151492 (The Pile)

Max Activating Token Index: 824