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

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

Neuron 2731 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0815. Min Act: -0.0004

Data Index: 459978 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0692. Min Act: -0.0004

Data Index: 1033430 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0722. Min Act: -0.0004

Data Index: 461738 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0733. Min Act: -0.0004

Data Index: 274329 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0590. Min Act: -0.0004

Data Index: 214270 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0668. Min Act: -0.0004

Data Index: 1107857 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0671. Min Act: -0.0004

Data Index: 1053808 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0658. Min Act: -0.0004

Data Index: 664886 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0642. Min Act: -0.0004

Data Index: 112784 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0571. Min Act: -0.0004

Data Index: 1173568 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0602. Min Act: -0.0004

Data Index: 160801 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0589. Min Act: -0.0004

Data Index: 774435 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0633. Min Act: -0.0004

Data Index: 922277 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0654. Min Act: -0.0004

Data Index: 699382 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0561. Min Act: -0.0004

Data Index: 616946 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0642. Min Act: -0.0004

Data Index: 468335 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0665. Min Act: -0.0004

Data Index: 1007627 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0645. Min Act: -0.0004

Data Index: 526571 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0592. Min Act: -0.0004

Data Index: 489846 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 0.0815. Min Range: -0.0815

Max Act: 0.0588. Min Act: -0.0004

Data Index: 143227 (C4 (Web Text))

Max Activating Token Index: 74