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

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

Neuron 2860 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5092. Min Act: -0.0000

Data Index: 399599 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1142546 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4828. Min Act: -0.0000

Data Index: 118592 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4758. Min Act: -0.0000

Data Index: 645881 (C4 (Web Text))

Max Activating Token Index: 388

Text #4

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4950. Min Act: -0.0000

Data Index: 474479 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4966. Min Act: -0.0000

Data Index: 209155 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4934. Min Act: -0.0000

Data Index: 792650 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4788. Min Act: -0.0000

Data Index: 432997 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4825. Min Act: -0.0000

Data Index: 466969 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.5036. Min Act: -0.0000

Data Index: 801175 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4819. Min Act: -0.0000

Data Index: 734954 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4509. Min Act: -0.0000

Data Index: 640959 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4582. Min Act: -0.0000

Data Index: 358288 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4559. Min Act: -0.0000

Data Index: 701208 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1293308 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4500. Min Act: -0.0000

Data Index: 648901 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4693. Min Act: -0.0000

Data Index: 731306 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4660. Min Act: -0.0000

Data Index: 941241 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4561. Min Act: -0.0000

Data Index: 644159 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 0.5410. Min Range: -0.5410

Max Act: 0.4702. Min Act: -0.0000

Data Index: 665992 (C4 (Web Text))

Max Activating Token Index: 331