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

Dataset: The Pile

Neuron 3001 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: 0.4014. Min Range: -0.4014

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1807905 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.4014. Min Act: -0.0000

Data Index: 788155 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2519. Min Act: -0.0000

Data Index: 460442 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1804200 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3695. Min Act: -0.0000

Data Index: 951036 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3439. Min Act: -0.0000

Data Index: 66105 (The Pile)

Max Activating Token Index: 787

Text #6

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1278120 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3630. Min Act: -0.0000

Data Index: 452174 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3711. Min Act: -0.0000

Data Index: 86224 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3752. Min Act: -0.0000

Data Index: 1139841 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3368. Min Act: -0.0000

Data Index: 304589 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3605. Min Act: -0.0000

Data Index: 64020 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3241. Min Act: -0.0000

Data Index: 513401 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1665139 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3004. Min Act: -0.0000

Data Index: 245003 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.2991. Min Act: -0.0000

Data Index: 636124 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3301. Min Act: -0.0000

Data Index: 706960 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1252916 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1443233 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 0.4014. Min Range: -0.4014

Max Act: 0.3164. Min Act: -0.0000

Data Index: 282463 (The Pile)

Max Activating Token Index: 310