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

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

Neuron 1229 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: 0.0848. Min Range: -0.0848

Max Act: 0.0787. Min Act: -0.0003

Data Index: 926688 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0758. Min Act: -0.0003

Data Index: 762885 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: -0.0003

Data Index: 265969 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0747. Min Act: -0.0003

Data Index: 1271073 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0631. Min Act: -0.0003

Data Index: 981526 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1068568 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0662. Min Act: -0.0003

Data Index: 580904 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0608. Min Act: -0.0003

Data Index: 164266 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0654. Min Act: -0.0003

Data Index: 609205 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0609. Min Act: -0.0003

Data Index: 440242 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0727. Min Act: -0.0003

Data Index: 508480 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0583. Min Act: -0.0003

Data Index: 568513 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0605. Min Act: -0.0003

Data Index: 957190 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0575. Min Act: -0.0003

Data Index: 463519 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0597. Min Act: -0.0003

Data Index: 144463 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0596. Min Act: -0.0003

Data Index: 937913 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1214381 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1305625 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0551. Min Act: -0.0003

Data Index: 738341 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0534. Min Act: -0.0003

Data Index: 739737 (C4 (Web Text))

Max Activating Token Index: 286