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

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

Neuron 2443 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.5009. Min Act: -0.0000

Data Index: 38813 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.5045. Min Act: -0.0000

Data Index: 1190398 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.0434. Min Act: -0.0000

Data Index: 568648 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.0791. Min Act: 0.0001

Data Index: 885847 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9471. Min Act: -0.0000

Data Index: 1270250 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.0257. Min Act: -0.0000

Data Index: 461327 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1279392 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.0323. Min Act: -0.0000

Data Index: 801522 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.0478. Min Act: -0.0000

Data Index: 730842 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1255244 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.0009. Min Act: 0.0000

Data Index: 1199543 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 1.5045. Min Range: -1.5045

Max Act: 1.0184. Min Act: -0.0000

Data Index: 763135 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9175. Min Act: -0.0000

Data Index: 608357 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9931. Min Act: -0.0000

Data Index: 328867 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9490. Min Act: -0.0000

Data Index: 210368 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.8991. Min Act: 0.0000

Data Index: 889857 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9216. Min Act: -0.0000

Data Index: 411480 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9158. Min Act: -0.0000

Data Index: 167881 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9637. Min Act: -0.0000

Data Index: 761794 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 1.5045. Min Range: -1.5045

Max Act: 0.9373. Min Act: -0.0000

Data Index: 507712 (C4 (Web Text))

Max Activating Token Index: 343