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

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

Neuron 2176 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1912. Min Act: -0.0002

Data Index: 379753 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1711. Min Act: -0.0002

Data Index: 600918 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1653. Min Act: -0.0002

Data Index: 163706 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1373. Min Act: -0.0002

Data Index: 628819 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1307. Min Act: -0.0002

Data Index: 182632 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1226. Min Act: -0.0002

Data Index: 1347218 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1226. Min Act: -0.0002

Data Index: 450655 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1038798 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1289112 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1093. Min Act: -0.0002

Data Index: 514666 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1110. Min Act: -0.0002

Data Index: 780245 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1069. Min Act: -0.0002

Data Index: 666749 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1064. Min Act: -0.0002

Data Index: 891044 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1017. Min Act: -0.0002

Data Index: 205926 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1085. Min Act: -0.0002

Data Index: 515748 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1073. Min Act: -0.0002

Data Index: 287130 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1011. Min Act: -0.0002

Data Index: 10214 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1023. Min Act: -0.0002

Data Index: 506235 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1015. Min Act: -0.0002

Data Index: 277926 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.0976. Min Act: -0.0002

Data Index: 585369 (C4 (Web Text))

Max Activating Token Index: 930