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

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

Neuron 1628 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.5396. Min Act: -0.0001

Data Index: 471535 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.6127. Min Act: -0.0001

Data Index: 1129735 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4206. Min Act: -0.0001

Data Index: 1164116 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4151. Min Act: -0.0001

Data Index: 1013679 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.3437. Min Act: -0.0001

Data Index: 1337156 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4252. Min Act: -0.0001

Data Index: 921586 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.4207. Min Act: -0.0001

Data Index: 184156 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.3558. Min Act: -0.0001

Data Index: 230649 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.3157. Min Act: -0.0001

Data Index: 1153180 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2941. Min Act: -0.0001

Data Index: 87882 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2888. Min Act: -0.0001

Data Index: 1000860 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2815. Min Act: -0.0001

Data Index: 730464 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2783. Min Act: -0.0001

Data Index: 68207 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2444. Min Act: -0.0001

Data Index: 143128 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2743. Min Act: -0.0001

Data Index: 640554 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2563. Min Act: -0.0001

Data Index: 808653 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.1805. Min Act: -0.0001

Data Index: 442256 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.3156. Min Act: -0.0001

Data Index: 184026 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2300. Min Act: -0.0001

Data Index: 31820 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 1.6127. Min Range: -1.6127

Max Act: 1.2628. Min Act: -0.0001

Data Index: 239017 (C4 (Web Text))

Max Activating Token Index: 86