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

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

Neuron 4869 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.6982. Min Act: -0.0000

Data Index: 293125 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.7353. Min Act: -0.0000

Data Index: 502762 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.7004. Min Act: -0.0000

Data Index: 523145 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.7812. Min Act: -0.0000

Data Index: 748399 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.6687. Min Act: -0.0000

Data Index: 261852 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.6795. Min Act: -0.0000

Data Index: 255687 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.6142. Min Act: -0.0000

Data Index: 933885 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5864. Min Act: -0.0000

Data Index: 127320 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5685. Min Act: -0.0000

Data Index: 216645 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.6120. Min Act: -0.0000

Data Index: 339083 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5422. Min Act: -0.0000

Data Index: 733803 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1207378 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5016. Min Act: -0.0000

Data Index: 113132 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.4851. Min Act: -0.0000

Data Index: 104794 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5128. Min Act: -0.0000

Data Index: 598150 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1092510 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.4963. Min Act: -0.0000

Data Index: 977170 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.4910. Min Act: -0.0000

Data Index: 780718 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.5095. Min Act: -0.0000

Data Index: 425764 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 0.7812. Min Range: -0.7812

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1169273 (C4 (Web Text))

Max Activating Token Index: 382