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

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

Neuron 2005 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: 1.1092. Min Range: -1.1092

Max Act: 1.1092. Min Act: -0.0000

Data Index: 34186 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 1.1092. Min Range: -1.1092

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1032750 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9755. Min Act: -0.0000

Data Index: 885996 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 1.1092. Min Range: -1.1092

Max Act: 1.0119. Min Act: -0.0000

Data Index: 3730 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9258. Min Act: -0.0000

Data Index: 697442 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9802. Min Act: -0.0000

Data Index: 403631 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.9699. Min Act: -0.0000

Data Index: 625236 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1036751 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8845. Min Act: -0.0000

Data Index: 1331450 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8567. Min Act: -0.0000

Data Index: 438765 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8518. Min Act: -0.0000

Data Index: 961023 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8979. Min Act: -0.0000

Data Index: 991433 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8665. Min Act: -0.0000

Data Index: 634351 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8830. Min Act: -0.0000

Data Index: 908294 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8625. Min Act: -0.0000

Data Index: 878444 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8068. Min Act: -0.0000

Data Index: 599368 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8516. Min Act: -0.0000

Data Index: 415564 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1320208 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8088. Min Act: -0.0000

Data Index: 816067 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 1.1092. Min Range: -1.1092

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1117918 (C4 (Web Text))

Max Activating Token Index: 683