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

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

Neuron 797 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: 1.6358. Min Range: -1.6358

Max Act: 1.6330. Min Act: -0.0000

Data Index: 1376562 (Python Code)

Max Activating Token Index: 640

Text #1

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5870. Min Act: -0.0000

Data Index: 1511692 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5856. Min Act: -0.0000

Data Index: 80920 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.6358. Min Act: -0.0000

Data Index: 715860 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5285. Min Act: -0.0000

Data Index: 1611347 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1606753 (Python Code)

Max Activating Token Index: 99

Text #6

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.4126. Min Act: -0.0000

Data Index: 1394273 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.3120. Min Act: -0.0000

Data Index: 1483159 (Python Code)

Max Activating Token Index: 857

Text #8

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1409806 (Python Code)

Max Activating Token Index: 845

Text #9

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1035592 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1592529 (Python Code)

Max Activating Token Index: 499

Text #11

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.2426. Min Act: -0.0000

Data Index: 1418818 (Python Code)

Max Activating Token Index: 387

Text #12

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1425245 (Python Code)

Max Activating Token Index: 474

Text #13

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1320425 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.3235. Min Act: -0.0000

Data Index: 1325393 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.2465. Min Act: -0.0000

Data Index: 1130939 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.3301. Min Act: -0.0000

Data Index: 1506227 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.2636. Min Act: -0.0000

Data Index: 954867 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.2175. Min Act: -0.0000

Data Index: 1369054 (Python Code)

Max Activating Token Index: 743

Text #19

Max Range: 1.6358. Min Range: -1.6358

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1646280 (Python Code)

Max Activating Token Index: 334