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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1337 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2822. Min Act: -0.0000

Data Index: 1158010 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2429. Min Act: -0.0000

Data Index: 2009 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2262. Min Act: -0.0000

Data Index: 992303 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2114. Min Act: -0.0000

Data Index: 687502 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2075. Min Act: -0.0000

Data Index: 544643 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2116. Min Act: -0.0000

Data Index: 836466 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2033. Min Act: -0.0000

Data Index: 310014 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1146304 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2095. Min Act: -0.0000

Data Index: 64388 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2016. Min Act: -0.0000

Data Index: 783304 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.1992. Min Act: -0.0000

Data Index: 469238 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2129. Min Act: -0.0000

Data Index: 280483 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.2107. Min Act: -0.0000

Data Index: 362950 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1116036 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.1961. Min Act: -0.0000

Data Index: 943721 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1234490 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1049513 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.1867. Min Act: -0.0000

Data Index: 924174 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.1908. Min Act: -0.0000

Data Index: 662154 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.2822. Min Range: -0.2822

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1155207 (C4 (Web Text))

Max Activating Token Index: 100