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

Dataset: The Pile

Neuron 1549 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: 2.8012. Min Range: -2.8012

Max Act: 2.8012. Min Act: -0.0000

Data Index: 1150217 (The Pile)

Max Activating Token Index: 960

Text #1

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.7799. Min Act: -0.0000

Data Index: 1710393 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.7270. Min Act: -0.0000

Data Index: 882290 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.6752. Min Act: -0.0000

Data Index: 1878974 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.5205. Min Act: -0.0000

Data Index: 1226312 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4639. Min Act: -0.0000

Data Index: 1758162 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4288. Min Act: -0.0000

Data Index: 945271 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4137. Min Act: -0.0000

Data Index: 896783 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.5047. Min Act: -0.0000

Data Index: 1692841 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4687. Min Act: -0.0000

Data Index: 727637 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4548. Min Act: -0.0000

Data Index: 575753 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4698. Min Act: -0.0000

Data Index: 841011 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4402. Min Act: -0.0000

Data Index: 565911 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4046. Min Act: -0.0000

Data Index: 152286 (The Pile)

Max Activating Token Index: 47

Text #14

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.4026. Min Act: -0.0000

Data Index: 1357327 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.3938. Min Act: -0.0000

Data Index: 1644244 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.3940. Min Act: 0.0001

Data Index: 807838 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.3837. Min Act: -0.0000

Data Index: 1125044 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.5053. Min Act: -0.0000

Data Index: 645694 (The Pile)

Max Activating Token Index: 848

Text #19

Max Range: 2.8012. Min Range: -2.8012

Max Act: 2.3721. Min Act: -0.0000

Data Index: 679449 (The Pile)

Max Activating Token Index: 582