Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5428. Min Act: -0.0001

Data Index: 641544 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5065. Min Act: -0.0001

Data Index: 1061573 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.5229. Min Act: -0.0001

Data Index: 1014164 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4984. Min Act: -0.0001

Data Index: 169688 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1079308 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4780. Min Act: -0.0001

Data Index: 383479 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4697. Min Act: -0.0001

Data Index: 824721 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1224431 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4560. Min Act: -0.0000

Data Index: 449120 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4108. Min Act: -0.0001

Data Index: 540180 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4558. Min Act: -0.0001

Data Index: 334743 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4809. Min Act: -0.0001

Data Index: 154655 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1344597 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1031759 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4304. Min Act: -0.0001

Data Index: 873537 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4691. Min Act: -0.0000

Data Index: 658472 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4268. Min Act: -0.0001

Data Index: 1198691 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4874. Min Act: -0.0001

Data Index: 1201363 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4850. Min Act: -0.0001

Data Index: 1085432 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.5428. Min Range: -0.5428

Max Act: 0.4543. Min Act: -0.0000

Data Index: 583796 (C4 (Web Text))

Max Activating Token Index: 138