Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1272 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3623. Min Act: -0.0001

Data Index: 1281970 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3451. Min Act: -0.0000

Data Index: 778788 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3356. Min Act: -0.0000

Data Index: 635327 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3008. Min Act: -0.0000

Data Index: 1312226 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2966. Min Act: -0.0001

Data Index: 658548 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2831. Min Act: -0.0001

Data Index: 541803 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2923. Min Act: -0.0001

Data Index: 359934 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2733. Min Act: -0.0000

Data Index: 207351 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2571. Min Act: -0.0000

Data Index: 930915 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2789. Min Act: -0.0001

Data Index: 26879 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1121266 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2318. Min Act: -0.0000

Data Index: 151916 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1123313 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2723. Min Act: -0.0000

Data Index: 481453 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2800. Min Act: -0.0000

Data Index: 922670 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1215616 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2498. Min Act: -0.0001

Data Index: 1309906 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1032311 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2360. Min Act: -0.0001

Data Index: 756663 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2469. Min Act: -0.0000

Data Index: 432394 (C4 (Web Text))

Max Activating Token Index: 112