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

Dataset: The Pile

Neuron 1589 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: 0.2732. Min Range: -0.2732

Max Act: 0.2732. Min Act: -0.0000

Data Index: 925227 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2685. Min Act: -0.0000

Data Index: 890370 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2280. Min Act: -0.0000

Data Index: 1530761 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1421918 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2105. Min Act: -0.0000

Data Index: 522375 (The Pile)

Max Activating Token Index: 1000

Text #5

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2217. Min Act: -0.0000

Data Index: 1721346 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2208. Min Act: -0.0000

Data Index: 572781 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1933785 (The Pile)

Max Activating Token Index: 138

Text #8

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1303943 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1871607 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1910. Min Act: -0.0000

Data Index: 42888 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2005. Min Act: -0.0000

Data Index: 975089 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2019. Min Act: -0.0000

Data Index: 648313 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1991. Min Act: -0.0000

Data Index: 930160 (The Pile)

Max Activating Token Index: 984

Text #14

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2049. Min Act: -0.0000

Data Index: 839865 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1133231 (The Pile)

Max Activating Token Index: 944

Text #16

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1882444 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1531737 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1787. Min Act: -0.0000

Data Index: 838405 (The Pile)

Max Activating Token Index: 827

Text #19

Max Range: 0.2732. Min Range: -0.2732

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1996024 (The Pile)

Max Activating Token Index: 55