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

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

Neuron 2747 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0838. Min Act: -0.0002

Data Index: 998136 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1092694 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1202056 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1012884 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0756. Min Act: -0.0002

Data Index: 744208 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0807. Min Act: -0.0002

Data Index: 1123268 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0818. Min Act: -0.0002

Data Index: 221276 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0834. Min Act: -0.0002

Data Index: 138083 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0806. Min Act: -0.0002

Data Index: 372451 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0808. Min Act: -0.0002

Data Index: 306216 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0798. Min Act: -0.0002

Data Index: 711918 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1254970 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0791. Min Act: -0.0002

Data Index: 435184 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0797. Min Act: -0.0002

Data Index: 307189 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0782. Min Act: -0.0002

Data Index: 736923 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0736. Min Act: -0.0002

Data Index: 879957 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0773. Min Act: -0.0002

Data Index: 762133 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0778. Min Act: -0.0002

Data Index: 445530 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0744. Min Act: -0.0002

Data Index: 1125257 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0838. Min Range: -0.0838

Max Act: 0.0747. Min Act: -0.0002

Data Index: 643313 (C4 (Web Text))

Max Activating Token Index: 414