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

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

Neuron 927 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1122244 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6443. Min Act: -0.0000

Data Index: 875393 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6362. Min Act: 0.0000

Data Index: 619104 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6550. Min Act: -0.0000

Data Index: 560509 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6268. Min Act: -0.0000

Data Index: 89990 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5680. Min Act: -0.0000

Data Index: 752550 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.6116. Min Act: -0.0000

Data Index: 94410 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1128531 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5833. Min Act: 0.0000

Data Index: 382550 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5210. Min Act: -0.0000

Data Index: 994526 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5697. Min Act: -0.0000

Data Index: 735827 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5478. Min Act: -0.0000

Data Index: 261454 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5464. Min Act: -0.0000

Data Index: 912651 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1251374 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5581. Min Act: -0.0000

Data Index: 20801 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5349. Min Act: -0.0000

Data Index: 580692 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5038. Min Act: -0.0000

Data Index: 876458 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5305. Min Act: -0.0000

Data Index: 640473 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5426. Min Act: 0.0000

Data Index: 865038 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.6641. Min Range: -0.6641

Max Act: 0.5229. Min Act: -0.0000

Data Index: 115636 (C4 (Web Text))

Max Activating Token Index: 863