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

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

Neuron 1439 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1129. Min Act: -0.0001

Data Index: 747547 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1137. Min Act: -0.0000

Data Index: 484311 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.1084. Min Act: -0.0001

Data Index: 118995 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0834. Min Act: -0.0000

Data Index: 334966 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1332685 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0855. Min Act: -0.0000

Data Index: 85667 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0806. Min Act: -0.0000

Data Index: 638923 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0884. Min Act: -0.0000

Data Index: 955588 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0888. Min Act: -0.0001

Data Index: 886244 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1291638 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1284726 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0852. Min Act: -0.0000

Data Index: 570188 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0837. Min Act: -0.0000

Data Index: 928225 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1251501 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0735. Min Act: -0.0000

Data Index: 886523 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0749. Min Act: -0.0001

Data Index: 656350 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0786. Min Act: -0.0001

Data Index: 528668 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0788. Min Act: -0.0001

Data Index: 684195 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1287047 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.1137. Min Range: -0.1137

Max Act: 0.0788. Min Act: -0.0001

Data Index: 813055 (C4 (Web Text))

Max Activating Token Index: 874