Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1731 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4863. Min Act: -0.0003

Data Index: 595078 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4407. Min Act: -0.0003

Data Index: 1034231 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4828. Min Act: -0.0003

Data Index: 1072528 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4411. Min Act: -0.0003

Data Index: 683522 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4365. Min Act: -0.0003

Data Index: 636087 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3998. Min Act: -0.0003

Data Index: 144796 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4108. Min Act: -0.0003

Data Index: 424663 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4108. Min Act: -0.0003

Data Index: 351843 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4056. Min Act: -0.0003

Data Index: 313670 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3857. Min Act: -0.0003

Data Index: 843874 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4008. Min Act: -0.0003

Data Index: 1265144 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4000. Min Act: -0.0003

Data Index: 171437 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4120. Min Act: -0.0003

Data Index: 619161 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3996. Min Act: -0.0003

Data Index: 826454 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4055. Min Act: -0.0003

Data Index: 1187443 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4051. Min Act: -0.0003

Data Index: 995215 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4012. Min Act: -0.0003

Data Index: 895809 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.4143. Min Act: -0.0003

Data Index: 751949 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3746. Min Act: -0.0003

Data Index: 350002 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.4863. Min Range: -0.4863

Max Act: 0.3876. Min Act: -0.0003

Data Index: 1167344 (C4 (Web Text))

Max Activating Token Index: 27