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

Dataset: The Pile

Neuron 174 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: 0.7034. Min Range: -0.7034

Max Act: 0.6723. Min Act: -0.0000

Data Index: 741815 (The Pile)

Max Activating Token Index: 736

Text #1

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.7034. Min Act: -0.0000

Data Index: 1570199 (The Pile)

Max Activating Token Index: 952

Text #2

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1516221 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6399. Min Act: -0.0000

Data Index: 268185 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6101. Min Act: -0.0000

Data Index: 989568 (The Pile)

Max Activating Token Index: 883

Text #5

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6578. Min Act: -0.0000

Data Index: 599285 (The Pile)

Max Activating Token Index: 990

Text #6

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1328974 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1639238 (The Pile)

Max Activating Token Index: 956

Text #8

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1185043 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5399. Min Act: -0.0000

Data Index: 995646 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.6038. Min Act: -0.0000

Data Index: 417245 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1722246 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5924. Min Act: -0.0000

Data Index: 991109 (The Pile)

Max Activating Token Index: 307

Text #13

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1581979 (The Pile)

Max Activating Token Index: 923

Text #14

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5540. Min Act: -0.0000

Data Index: 149658 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1831519 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5576. Min Act: -0.0000

Data Index: 558706 (The Pile)

Max Activating Token Index: 883

Text #17

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5337. Min Act: -0.0000

Data Index: 770639 (The Pile)

Max Activating Token Index: 900

Text #18

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1574177 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 0.7034. Min Range: -0.7034

Max Act: 0.4567. Min Act: -0.0000

Data Index: 16641 (The Pile)

Max Activating Token Index: 748