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

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

Neuron 4727 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: 0.1196. Min Range: -0.1196

Max Act: 0.1196. Min Act: -0.0002

Data Index: 694132 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1081. Min Act: -0.0002

Data Index: 332360 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1101. Min Act: -0.0002

Data Index: 893768 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0988. Min Act: -0.0002

Data Index: 488744 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0930. Min Act: -0.0002

Data Index: 477136 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1233625 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0960. Min Act: -0.0002

Data Index: 29848 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0988. Min Act: -0.0002

Data Index: 358125 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0947. Min Act: -0.0002

Data Index: 908825 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0912. Min Act: -0.0002

Data Index: 513960 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0912. Min Act: -0.0002

Data Index: 836059 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0750. Min Act: -0.0002

Data Index: 397566 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1269329 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0897. Min Act: -0.0002

Data Index: 496829 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0861. Min Act: -0.0002

Data Index: 335611 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0713. Min Act: -0.0002

Data Index: 30717 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0877. Min Act: -0.0002

Data Index: 387388 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0838. Min Act: -0.0002

Data Index: 28240 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0905. Min Act: -0.0002

Data Index: 66791 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1070180 (C4 (Web Text))

Max Activating Token Index: 972