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

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

Neuron 3461 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: 0.6851. Min Range: -0.6851

Max Act: 0.6851. Min Act: -0.0000

Data Index: 237456 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.6062. Min Act: -0.0000

Data Index: 460897 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1293948 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1235081 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1060636 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5594. Min Act: -0.0000

Data Index: 475848 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5219. Min Act: -0.0000

Data Index: 948487 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1064570 (C4 (Web Text))

Max Activating Token Index: 626

Text #8

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1151034 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1016882 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5109. Min Act: -0.0000

Data Index: 374694 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5104. Min Act: -0.0000

Data Index: 477060 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4945. Min Act: -0.0000

Data Index: 431592 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1233867 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5141. Min Act: -0.0000

Data Index: 596872 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5063. Min Act: -0.0000

Data Index: 234138 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5261. Min Act: -0.0000

Data Index: 415694 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1163725 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1301853 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.6851. Min Range: -0.6851

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1248996 (C4 (Web Text))

Max Activating Token Index: 440