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

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

Neuron 821 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5558. Min Range: -2.5558

Max Act: 2.5558. Min Act: 0.0000

Data Index: 1297473 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 2.5558. Min Range: -2.5558

Max Act: 2.4410. Min Act: -0.0000

Data Index: 454215 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 2.5558. Min Range: -2.5558

Max Act: 2.2874. Min Act: -0.0000

Data Index: 58978 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 2.5558. Min Range: -2.5558

Max Act: 2.2137. Min Act: 0.0001

Data Index: 456836 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 2.5558. Min Range: -2.5558

Max Act: 2.0378. Min Act: -0.0000

Data Index: 1040179 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.8257. Min Act: -0.0000

Data Index: 206754 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.9914. Min Act: -0.0000

Data Index: 488322 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.9031. Min Act: -0.0000

Data Index: 368826 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.9383. Min Act: 0.0001

Data Index: 93805 (C4 (Web Text))

Max Activating Token Index: 792

Text #9

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.8397. Min Act: -0.0000

Data Index: 466172 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.7165. Min Act: -0.0000

Data Index: 757436 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.8967. Min Act: -0.0000

Data Index: 790988 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.7023. Min Act: -0.0000

Data Index: 45581 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.8721. Min Act: -0.0000

Data Index: 964030 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.6738. Min Act: 0.0000

Data Index: 796293 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.7211. Min Act: -0.0000

Data Index: 111882 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.7337. Min Act: -0.0000

Data Index: 962075 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.6621. Min Act: -0.0000

Data Index: 813552 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.6946. Min Act: -0.0000

Data Index: 1066849 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 2.5558. Min Range: -2.5558

Max Act: 1.6835. Min Act: -0.0000

Data Index: 1136232 (C4 (Web Text))

Max Activating Token Index: 169