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

Dataset: The Pile

Neuron 2480 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7822. Min Range: -3.7822

Max Act: 3.7782. Min Act: -0.0000

Data Index: 1383796 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 3.7822. Min Range: -3.7822

Max Act: 3.7822. Min Act: -0.0000

Data Index: 1731373 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 3.7822. Min Range: -3.7822

Max Act: 3.3641. Min Act: -0.0000

Data Index: 310039 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 3.7822. Min Range: -3.7822

Max Act: 3.0532. Min Act: -0.0000

Data Index: 600251 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 3.7822. Min Range: -3.7822

Max Act: 3.1381. Min Act: -0.0000

Data Index: 995940 (The Pile)

Max Activating Token Index: 202

Text #5

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.7967. Min Act: -0.0000

Data Index: 1014597 (The Pile)

Max Activating Token Index: 899

Text #6

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.4681. Min Act: -0.0000

Data Index: 190057 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.7924. Min Act: -0.0000

Data Index: 1031425 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.7691. Min Act: -0.0000

Data Index: 1801538 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.9317. Min Act: -0.0000

Data Index: 889267 (The Pile)

Max Activating Token Index: 286

Text #10

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.8273. Min Act: -0.0000

Data Index: 1771813 (The Pile)

Max Activating Token Index: 159

Text #11

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.6828. Min Act: -0.0000

Data Index: 813569 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.9009. Min Act: -0.0000

Data Index: 936399 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.6558. Min Act: -0.0000

Data Index: 1691773 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.9354. Min Act: -0.0000

Data Index: 1119037 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.7695. Min Act: -0.0000

Data Index: 732249 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 3.7822. Min Range: -3.7822

Max Act: 3.1643. Min Act: -0.0000

Data Index: 612740 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.7545. Min Act: -0.0000

Data Index: 1900461 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 3.7822. Min Range: -3.7822

Max Act: 3.0381. Min Act: -0.0000

Data Index: 1833195 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 3.7822. Min Range: -3.7822

Max Act: 2.7558. Min Act: -0.0000

Data Index: 1999302 (The Pile)

Max Activating Token Index: 461