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

Dataset: The Pile

Neuron 1681 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1589. Min Act: -0.0000

Data Index: 496454 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1090. Min Act: -0.0000

Data Index: 22299 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1969512 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0866. Min Act: -0.0000

Data Index: 961544 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0949. Min Act: -0.0000

Data Index: 1975987 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0926. Min Act: -0.0000

Data Index: 751135 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0939. Min Act: -0.0000

Data Index: 615603 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0912. Min Act: -0.0000

Data Index: 293941 (The Pile)

Max Activating Token Index: 459

Text #8

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0950. Min Act: -0.0000

Data Index: 199758 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1159092 (The Pile)

Max Activating Token Index: 959

Text #10

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0859. Min Act: 0.0000

Data Index: 312767 (The Pile)

Max Activating Token Index: 123

Text #11

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0877. Min Act: -0.0000

Data Index: 493248 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0870. Min Act: -0.0000

Data Index: 508282 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1789534 (The Pile)

Max Activating Token Index: 158

Text #14

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1067196 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0858. Min Act: -0.0000

Data Index: 375363 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0790. Min Act: -0.0000

Data Index: 593333 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1866865 (The Pile)

Max Activating Token Index: 297

Text #18

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0785. Min Act: -0.0000

Data Index: 768387 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1060344 (The Pile)

Max Activating Token Index: 648