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

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

Neuron 1835 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.8525. Min Act: -0.0000

Data Index: 996182 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7710. Min Act: -0.0000

Data Index: 936461 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1161726 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7619. Min Act: -0.0000

Data Index: 902269 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7489. Min Act: -0.0000

Data Index: 52918 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1046130 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1320213 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1010970 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7393. Min Act: -0.0000

Data Index: 279038 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7015. Min Act: -0.0000

Data Index: 511972 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7030. Min Act: -0.0000

Data Index: 87327 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.8190. Min Act: -0.0000

Data Index: 777753 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1087167 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7109. Min Act: -0.0000

Data Index: 894367 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1077747 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.7176. Min Act: -0.0000

Data Index: 159536 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.6804. Min Act: -0.0000

Data Index: 501397 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.6387. Min Act: -0.0000

Data Index: 791433 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.6791. Min Act: -0.0000

Data Index: 975720 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.8525. Min Range: -0.8525

Max Act: 0.6115. Min Act: -0.0000

Data Index: 922089 (C4 (Web Text))

Max Activating Token Index: 1000