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

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

Neuron 1256 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6834. Min Act: -0.0000

Data Index: 73343 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1149683 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5403. Min Act: -0.0000

Data Index: 113296 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5061. Min Act: -0.0000

Data Index: 80653 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1015962 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5012. Min Act: -0.0000

Data Index: 370822 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1278861 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5217. Min Act: -0.0000

Data Index: 476863 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5211. Min Act: -0.0000

Data Index: 109170 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5377. Min Act: -0.0000

Data Index: 357879 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1104061 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5212. Min Act: -0.0000

Data Index: 101163 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5093. Min Act: -0.0000

Data Index: 405314 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5073. Min Act: -0.0000

Data Index: 738452 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5019. Min Act: -0.0000

Data Index: 424399 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4977. Min Act: -0.0000

Data Index: 63296 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1160826 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4971. Min Act: -0.0000

Data Index: 618423 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4682. Min Act: -0.0000

Data Index: 709828 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1108666 (C4 (Web Text))

Max Activating Token Index: 894