Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6147. Min Act: -0.0001

Data Index: 190606 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6419. Min Act: -0.0001

Data Index: 679834 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5822. Min Act: -0.0001

Data Index: 163902 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5619. Min Act: -0.0001

Data Index: 1186690 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5719. Min Act: -0.0001

Data Index: 871727 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5644. Min Act: -0.0001

Data Index: 64687 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5917. Min Act: -0.0001

Data Index: 1314193 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6132. Min Act: -0.0001

Data Index: 1247402 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5712. Min Act: -0.0001

Data Index: 38077 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5534. Min Act: -0.0001

Data Index: 693702 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5480. Min Act: -0.0001

Data Index: 392392 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5260. Min Act: -0.0001

Data Index: 319574 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5349. Min Act: -0.0001

Data Index: 83350 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5390. Min Act: -0.0001

Data Index: 301832 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6077. Min Act: -0.0001

Data Index: 475883 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4654. Min Act: -0.0001

Data Index: 246287 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4780. Min Act: -0.0001

Data Index: 690809 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4797. Min Act: -0.0001

Data Index: 889628 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4774. Min Act: -0.0001

Data Index: 616504 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5027. Min Act: -0.0001

Data Index: 160058 (C4 (Web Text))

Max Activating Token Index: 912