Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 93 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1244. Min Act: -0.0000

Data Index: 555788 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1599348 (Python Code)

Max Activating Token Index: 827

Text #2

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1181. Min Act: -0.0000

Data Index: 799885 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1269437 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1116. Min Act: -0.0000

Data Index: 568732 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1130. Min Act: -0.0000

Data Index: 979183 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1285550 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1242745 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1048. Min Act: -0.0000

Data Index: 931102 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1054. Min Act: -0.0000

Data Index: 361381 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1014. Min Act: -0.0000

Data Index: 215941 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1015. Min Act: -0.0000

Data Index: 165836 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1115. Min Act: -0.0000

Data Index: 858029 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1027. Min Act: -0.0000

Data Index: 138721 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1059631 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0978. Min Act: -0.0000

Data Index: 987259 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0976. Min Act: -0.0000

Data Index: 634385 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1433878 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0995. Min Act: -0.0000

Data Index: 91043 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1029. Min Act: -0.0000

Data Index: 101777 (C4 (Web Text))

Max Activating Token Index: 351