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

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

Neuron 4081 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: 0.0779. Min Range: -0.0779

Max Act: 0.0771. Min Act: -0.0000

Data Index: 639853 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1553885 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1358641 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1059492 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1050032 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1186201 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0630. Min Act: -0.0000

Data Index: 671178 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0510. Min Act: -0.0000

Data Index: 228418 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1577656 (Python Code)

Max Activating Token Index: 693

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0552. Min Act: -0.0000

Data Index: 1629014 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0598. Min Act: -0.0000

Data Index: 10608 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0553. Min Act: -0.0000

Data Index: 1493699 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0551. Min Act: -0.0000

Data Index: 54049 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1336075 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1652610 (Python Code)

Max Activating Token Index: 942

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1045726 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1519146 (Python Code)

Max Activating Token Index: 345

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0536. Min Act: -0.0000

Data Index: 440556 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0530. Min Act: -0.0000

Data Index: 824844 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0465. Min Act: -0.0000

Data Index: 1129495 (C4 (Web Text))

Max Activating Token Index: 932