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

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

Neuron 211 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: 0.7422. Min Range: -0.7422

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1251763 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5558. Min Act: 0.0001

Data Index: 381884 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5405. Min Act: -0.0000

Data Index: 892299 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5550. Min Act: -0.0000

Data Index: 366413 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5440. Min Act: -0.0000

Data Index: 836747 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5252. Min Act: -0.0000

Data Index: 694949 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5081. Min Act: 0.0001

Data Index: 433131 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5405. Min Act: -0.0000

Data Index: 722055 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5357. Min Act: -0.0000

Data Index: 918333 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5499. Min Act: -0.0000

Data Index: 45709 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1097653 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1074371 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1323735 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4734. Min Act: -0.0000

Data Index: 80117 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4708. Min Act: -0.0000

Data Index: 626938 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4672. Min Act: -0.0000

Data Index: 783319 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4665. Min Act: -0.0000

Data Index: 908989 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4300. Min Act: -0.0000

Data Index: 664244 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4279. Min Act: -0.0000

Data Index: 358173 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.7422. Min Range: -0.7422

Max Act: 0.4148. Min Act: -0.0000

Data Index: 532768 (C4 (Web Text))

Max Activating Token Index: 855