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

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

Neuron 5824 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1277722 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6520. Min Act: -0.0000

Data Index: 284277 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.6340. Min Act: -0.0000

Data Index: 538547 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1126662 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5762. Min Act: -0.0000

Data Index: 798666 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5820. Min Act: -0.0000

Data Index: 625852 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5430. Min Act: -0.0000

Data Index: 110629 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5628. Min Act: -0.0000

Data Index: 227436 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5173. Min Act: -0.0000

Data Index: 87183 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5402. Min Act: -0.0000

Data Index: 22019 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5055. Min Act: -0.0000

Data Index: 534997 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4903. Min Act: -0.0000

Data Index: 212961 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5372. Min Act: -0.0000

Data Index: 336773 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5175. Min Act: -0.0000

Data Index: 973990 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4823. Min Act: -0.0000

Data Index: 331955 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5121. Min Act: -0.0000

Data Index: 723475 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5449. Min Act: -0.0000

Data Index: 110209 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1070822 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.4737. Min Act: -0.0000

Data Index: 838375 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 0.7600. Min Range: -0.7600

Max Act: 0.5011. Min Act: -0.0000

Data Index: 359995 (C4 (Web Text))

Max Activating Token Index: 330