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

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

Neuron 3128 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: 1.0884. Min Range: -1.0884

Max Act: 1.0884. Min Act: 0.0000

Data Index: 1314016 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8829. Min Act: -0.0000

Data Index: 104353 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1206055 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.6981. Min Act: -0.0000

Data Index: 325354 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8369. Min Act: -0.0000

Data Index: 624698 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8028. Min Act: -0.0000

Data Index: 148840 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8752. Min Act: -0.0000

Data Index: 427820 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.8207. Min Act: -0.0000

Data Index: 740048 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7825. Min Act: -0.0000

Data Index: 347795 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7686. Min Act: -0.0000

Data Index: 3523 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7675. Min Act: -0.0000

Data Index: 1293678 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1173443 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1062624 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7543. Min Act: -0.0000

Data Index: 360841 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7835. Min Act: -0.0000

Data Index: 781439 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1049944 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7077. Min Act: -0.0000

Data Index: 747805 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1295060 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7134. Min Act: -0.0000

Data Index: 664122 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 1.0884. Min Range: -1.0884

Max Act: 0.7323. Min Act: -0.0000

Data Index: 965030 (C4 (Web Text))

Max Activating Token Index: 431