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

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

Neuron 5083 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: 0.0915. Min Range: -0.0915

Max Act: 0.0915. Min Act: -0.0002

Data Index: 725752 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0869. Min Act: -0.0002

Data Index: 888298 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0834. Min Act: -0.0002

Data Index: 374942 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0836. Min Act: -0.0002

Data Index: 401110 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0768. Min Act: -0.0002

Data Index: 133485 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0771. Min Act: -0.0002

Data Index: 414571 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0796. Min Act: -0.0002

Data Index: 774066 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1088598 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0761. Min Act: -0.0002

Data Index: 81161 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0778. Min Act: -0.0002

Data Index: 948745 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1301302 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0802. Min Act: -0.0002

Data Index: 702262 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0775. Min Act: -0.0002

Data Index: 75902 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0763. Min Act: -0.0002

Data Index: 953236 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0753. Min Act: -0.0002

Data Index: 625636 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0747. Min Act: -0.0002

Data Index: 949275 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0745. Min Act: -0.0002

Data Index: 298102 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0742. Min Act: -0.0002

Data Index: 1331292 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0729. Min Act: -0.0002

Data Index: 185918 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0915. Min Range: -0.0915

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1277617 (C4 (Web Text))

Max Activating Token Index: 372