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

Dataset: The Pile

Neuron 4958 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: 1.8284. Min Range: -1.8284

Max Act: 1.8284. Min Act: -0.0000

Data Index: 693804 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3899. Min Act: -0.0000

Data Index: 12737 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.7477. Min Act: -0.0000

Data Index: 1050478 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.6354. Min Act: -0.0000

Data Index: 81370 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.6776. Min Act: -0.0000

Data Index: 1431350 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1389994 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.4497. Min Act: -0.0000

Data Index: 817576 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.5117. Min Act: -0.0000

Data Index: 17643 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.4012. Min Act: -0.0000

Data Index: 495791 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1038791 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1991866 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.4671. Min Act: -0.0000

Data Index: 1760962 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.2862. Min Act: -0.0000

Data Index: 544033 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1916700 (The Pile)

Max Activating Token Index: 941

Text #14

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1822289 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3859. Min Act: -0.0000

Data Index: 1227822 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3942. Min Act: -0.0000

Data Index: 593987 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.3904. Min Act: -0.0000

Data Index: 1551212 (The Pile)

Max Activating Token Index: 14

Text #18

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.2284. Min Act: -0.0000

Data Index: 533242 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.8284. Min Range: -1.8284

Max Act: 1.2992. Min Act: -0.0000

Data Index: 1469135 (The Pile)

Max Activating Token Index: 976