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

Dataset: The Pile

Neuron 3305 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1870688 (The Pile)

Max Activating Token Index: 448

Text #1

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1211019 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1647213 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1540939 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1450425 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.9060. Min Act: -0.0000

Data Index: 813163 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1741296 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1501513 (The Pile)

Max Activating Token Index: 818

Text #8

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1062611 (The Pile)

Max Activating Token Index: 337

Text #9

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8740. Min Act: -0.0000

Data Index: 1310655 (The Pile)

Max Activating Token Index: 315

Text #10

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8770. Min Act: -0.0000

Data Index: 415924 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1003118 (The Pile)

Max Activating Token Index: 801

Text #12

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8510. Min Act: -0.0000

Data Index: 947896 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8269. Min Act: -0.0000

Data Index: 550543 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8464. Min Act: -0.0000

Data Index: 782959 (The Pile)

Max Activating Token Index: 193

Text #15

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1568287 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1927272 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8223. Min Act: -0.0000

Data Index: 605409 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8019. Min Act: -0.0000

Data Index: 699060 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 0.9736. Min Range: -0.9736

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1143554 (The Pile)

Max Activating Token Index: 591