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

Dataset: The Pile

Neuron 1834 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: 1.5912. Min Range: -1.5912

Max Act: 1.5912. Min Act: -0.0000

Data Index: 935380 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.3690. Min Act: -0.0000

Data Index: 331909 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.3569. Min Act: -0.0000

Data Index: 1967451 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.2276. Min Act: -0.0000

Data Index: 319298 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.1935. Min Act: -0.0000

Data Index: 366042 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.2223. Min Act: -0.0000

Data Index: 1085802 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.3010. Min Act: -0.0000

Data Index: 599859 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1634683 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1321646 (The Pile)

Max Activating Token Index: 130

Text #9

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.0862. Min Act: -0.0000

Data Index: 833834 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.1123. Min Act: -0.0000

Data Index: 1327000 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1378709 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1354161 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1546524 (The Pile)

Max Activating Token Index: 729

Text #14

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.1770. Min Act: -0.0000

Data Index: 203988 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1720986 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.0975. Min Act: -0.0000

Data Index: 725417 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.0972. Min Act: -0.0000

Data Index: 1479067 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.0856. Min Act: -0.0000

Data Index: 329291 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 1.5912. Min Range: -1.5912

Max Act: 1.0904. Min Act: -0.0000

Data Index: 273153 (The Pile)

Max Activating Token Index: 288