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

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

Neuron 3795 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1211. Min Act: -0.0001

Data Index: 235610 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1025. Min Act: -0.0002

Data Index: 111372 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.1104. Min Act: -0.0001

Data Index: 336366 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0970. Min Act: -0.0002

Data Index: 425534 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0948. Min Act: -0.0002

Data Index: 822042 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0954. Min Act: -0.0002

Data Index: 50580 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0901. Min Act: -0.0001

Data Index: 114552 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1138469 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1255737 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1179169 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1239991 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1237799 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0838. Min Act: -0.0002

Data Index: 532581 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0823. Min Act: -0.0002

Data Index: 781328 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0838. Min Act: -0.0002

Data Index: 180141 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0794. Min Act: -0.0001

Data Index: 655677 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1280897 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0822. Min Act: -0.0002

Data Index: 346696 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0809. Min Act: -0.0002

Data Index: 560750 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.1211. Min Range: -0.1211

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1157521 (C4 (Web Text))

Max Activating Token Index: 259