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

Dataset: The Pile

Neuron 2150 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1057. Min Range: -1.1057

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1752935 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.9934. Min Act: -0.0000

Data Index: 913936 (The Pile)

Max Activating Token Index: 437

Text #2

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1342851 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1741896 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1728144 (The Pile)

Max Activating Token Index: 516

Text #5

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8717. Min Act: -0.0000

Data Index: 754296 (The Pile)

Max Activating Token Index: 104

Text #6

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.9186. Min Act: -0.0000

Data Index: 1735107 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8599. Min Act: -0.0000

Data Index: 113673 (The Pile)

Max Activating Token Index: 648

Text #8

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.9290. Min Act: -0.0000

Data Index: 72537 (The Pile)

Max Activating Token Index: 678

Text #9

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1291644 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8791. Min Act: -0.0000

Data Index: 584239 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8759. Min Act: -0.0000

Data Index: 280130 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1070303 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1872688 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1052246 (The Pile)

Max Activating Token Index: 944

Text #15

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1113892 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8309. Min Act: -0.0000

Data Index: 694616 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8320. Min Act: -0.0000

Data Index: 721011 (The Pile)

Max Activating Token Index: 153

Text #18

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8474. Min Act: -0.0000

Data Index: 575995 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 1.1057. Min Range: -1.1057

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1800771 (The Pile)

Max Activating Token Index: 148