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

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

Neuron 3242 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: 0.0982. Min Range: -0.0982

Max Act: 0.0884. Min Act: -0.0003

Data Index: 7798 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0982. Min Act: -0.0003

Data Index: 365032 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0914. Min Act: -0.0003

Data Index: 195207 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0867. Min Act: -0.0003

Data Index: 428994 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0929. Min Act: -0.0003

Data Index: 109993 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0876. Min Act: -0.0003

Data Index: 797622 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0870. Min Act: -0.0003

Data Index: 477110 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0832. Min Act: -0.0003

Data Index: 1215459 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0836. Min Act: -0.0003

Data Index: 32472 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0856. Min Act: -0.0003

Data Index: 585508 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0860. Min Act: -0.0003

Data Index: 562504 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0882. Min Act: -0.0003

Data Index: 280742 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0850. Min Act: -0.0003

Data Index: 202640 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0875. Min Act: -0.0003

Data Index: 1320548 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0867. Min Act: -0.0003

Data Index: 992036 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1190825 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0829. Min Act: -0.0003

Data Index: 389006 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0855. Min Act: -0.0003

Data Index: 217961 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0755. Min Act: -0.0003

Data Index: 1192613 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0850. Min Act: -0.0003

Data Index: 160932 (C4 (Web Text))

Max Activating Token Index: 713