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

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

Neuron 3771 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3644. Min Act: -0.0000

Data Index: 584790 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.1893. Min Act: -0.0000

Data Index: 498450 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.0979. Min Act: -0.0000

Data Index: 1245592 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.1030. Min Act: -0.0000

Data Index: 1353890 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.0193. Min Act: -0.0000

Data Index: 1218585 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.0870. Min Act: -0.0000

Data Index: 859739 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9468. Min Act: -0.0000

Data Index: 838606 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.0211. Min Act: -0.0000

Data Index: 344035 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9700. Min Act: -0.0000

Data Index: 913553 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9793. Min Act: -0.0000

Data Index: 656460 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1003823 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9614. Min Act: -0.0000

Data Index: 293439 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8995. Min Act: -0.0000

Data Index: 339411 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1229639 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9023. Min Act: -0.0000

Data Index: 915598 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1185988 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8997. Min Act: -0.0000

Data Index: 184332 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9173. Min Act: -0.0000

Data Index: 255447 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8784. Min Act: -0.0000

Data Index: 865458 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8808. Min Act: -0.0000

Data Index: 895603 (C4 (Web Text))

Max Activating Token Index: 135