Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 216 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.6045. Min Act: -0.0000

Data Index: 377052 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.4259. Min Act: -0.0000

Data Index: 314970 (The Pile)

Max Activating Token Index: 755

Text #2

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.1929. Min Act: -0.0000

Data Index: 437633 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.2005. Min Act: -0.0000

Data Index: 1039226 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.2094. Min Act: -0.0000

Data Index: 367532 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.0318. Min Act: -0.0000

Data Index: 1345309 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.0390. Min Act: -0.0000

Data Index: 1590327 (The Pile)

Max Activating Token Index: 115

Text #7

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.1783. Min Act: -0.0000

Data Index: 1606630 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 3.6045. Min Range: -3.6045

Max Act: 3.1846. Min Act: -0.0000

Data Index: 614510 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.9875. Min Act: -0.0000

Data Index: 156682 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.7996. Min Act: -0.0000

Data Index: 1966473 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.6412. Min Act: -0.0000

Data Index: 1120975 (The Pile)

Max Activating Token Index: 768

Text #12

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.8585. Min Act: -0.0000

Data Index: 1878498 (The Pile)

Max Activating Token Index: 656

Text #13

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.8485. Min Act: -0.0000

Data Index: 1220320 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.9501. Min Act: -0.0000

Data Index: 1536445 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.5700. Min Act: -0.0000

Data Index: 247807 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.8090. Min Act: -0.0000

Data Index: 1017890 (The Pile)

Max Activating Token Index: 44

Text #17

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.6601. Min Act: -0.0000

Data Index: 1872136 (The Pile)

Max Activating Token Index: 90

Text #18

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.7752. Min Act: -0.0000

Data Index: 842318 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 3.6045. Min Range: -3.6045

Max Act: 2.6218. Min Act: -0.0000

Data Index: 1828808 (The Pile)

Max Activating Token Index: 17