Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1944 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0003

Data Index: 188850 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0644. Min Act: -0.0003

Data Index: 866956 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0610. Min Act: -0.0003

Data Index: 904601 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0626. Min Act: -0.0003

Data Index: 928246 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0587. Min Act: -0.0003

Data Index: 741410 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0582. Min Act: -0.0003

Data Index: 26466 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0560. Min Act: -0.0003

Data Index: 156024 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0520. Min Act: -0.0003

Data Index: 40106 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0561. Min Act: -0.0003

Data Index: 990369 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0536. Min Act: -0.0003

Data Index: 481706 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0536. Min Act: -0.0003

Data Index: 661144 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0526. Min Act: -0.0003

Data Index: 915418 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0543. Min Act: -0.0003

Data Index: 583374 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0576. Min Act: -0.0003

Data Index: 24378 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1024722 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0538. Min Act: -0.0003

Data Index: 508573 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1154720 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0562. Min Act: -0.0003

Data Index: 186487 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0535. Min Act: -0.0003

Data Index: 395816 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1192771 (C4 (Web Text))

Max Activating Token Index: 455