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

Dataset: The Pile

Neuron 2075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1298050 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1603475 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1296870 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2321. Min Act: -0.0000

Data Index: 196129 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1202119 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1345227 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2560. Min Act: -0.0000

Data Index: 191798 (The Pile)

Max Activating Token Index: 59

Text #7

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2168. Min Act: -0.0000

Data Index: 547795 (The Pile)

Max Activating Token Index: 233

Text #8

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1895190 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1441197 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1552013 (The Pile)

Max Activating Token Index: 314

Text #11

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.1865. Min Act: -0.0000

Data Index: 7348 (The Pile)

Max Activating Token Index: 990

Text #12

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1884673 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.1880. Min Act: -0.0000

Data Index: 405755 (The Pile)

Max Activating Token Index: 475

Text #14

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2000. Min Act: -0.0000

Data Index: 819028 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2017. Min Act: -0.0000

Data Index: 647306 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.1797. Min Act: -0.0000

Data Index: 944910 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1133293 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1486887 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2073. Min Act: -0.0000

Data Index: 1456461 (The Pile)

Max Activating Token Index: 820