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

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

Neuron 1810 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8504. Min Act: -0.0001

Data Index: 277961 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7141. Min Act: -0.0001

Data Index: 1176771 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7033. Min Act: -0.0001

Data Index: 999284 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6671. Min Act: -0.0001

Data Index: 156683 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6898. Min Act: -0.0001

Data Index: 674263 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7107. Min Act: -0.0001

Data Index: 924326 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6879. Min Act: -0.0001

Data Index: 720923 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6624. Min Act: -0.0001

Data Index: 1209456 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6751. Min Act: -0.0001

Data Index: 181534 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6475. Min Act: -0.0001

Data Index: 773251 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6529. Min Act: -0.0001

Data Index: 801354 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6252. Min Act: -0.0001

Data Index: 50607 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6552. Min Act: -0.0001

Data Index: 115907 (C4 (Web Text))

Max Activating Token Index: 222

Text #13

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6237. Min Act: -0.0001

Data Index: 377470 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6170. Min Act: -0.0001

Data Index: 423441 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6158. Min Act: -0.0001

Data Index: 792656 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6172. Min Act: -0.0001

Data Index: 309884 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5938. Min Act: -0.0001

Data Index: 1271721 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5955. Min Act: -0.0001

Data Index: 149138 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6125. Min Act: -0.0001

Data Index: 960929 (C4 (Web Text))

Max Activating Token Index: 152