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

Dataset: The Pile

Neuron 5051 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: 1.1626. Min Range: -1.1626

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1218477 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.1626. Min Act: -0.0000

Data Index: 1759050 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.0709. Min Act: -0.0000

Data Index: 302205 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1455286 (The Pile)

Max Activating Token Index: 869

Text #4

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.0392. Min Act: -0.0000

Data Index: 1518036 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.0331. Min Act: -0.0000

Data Index: 948118 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 1.1626. Min Range: -1.1626

Max Act: 1.0048. Min Act: -0.0000

Data Index: 1105281 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9531. Min Act: -0.0000

Data Index: 936860 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9028. Min Act: -0.0000

Data Index: 364132 (The Pile)

Max Activating Token Index: 571

Text #9

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1321731 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9716. Min Act: -0.0000

Data Index: 741557 (The Pile)

Max Activating Token Index: 59

Text #11

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9062. Min Act: -0.0000

Data Index: 1938900 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1478414 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.8896. Min Act: -0.0000

Data Index: 1136325 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1101756 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1968924 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.8998. Min Act: 0.0001

Data Index: 506239 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.8755. Min Act: -0.0000

Data Index: 362774 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1235757 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 1.1626. Min Range: -1.1626

Max Act: 0.7889. Min Act: 0.0000

Data Index: 1361560 (The Pile)

Max Activating Token Index: 899