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

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

Neuron 1708 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: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1350831 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1111974 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0733. Min Act: -0.0001

Data Index: 494121 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0759. Min Act: -0.0001

Data Index: 495448 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0643. Min Act: -0.0001

Data Index: 416417 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0703. Min Act: -0.0001

Data Index: 832582 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1264316 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0551. Min Act: -0.0001

Data Index: 1101599 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0629. Min Act: -0.0001

Data Index: 63395 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0663. Min Act: -0.0001

Data Index: 110218 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1119739 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0583. Min Act: -0.0001

Data Index: 626651 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0509. Min Act: -0.0001

Data Index: 42508 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1532757 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0621. Min Act: -0.0001

Data Index: 381343 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0524. Min Act: -0.0001

Data Index: 484949 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0549. Min Act: -0.0001

Data Index: 390859 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0538. Min Act: -0.0001

Data Index: 426438 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0550. Min Act: -0.0001

Data Index: 1268906 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0573. Min Act: -0.0001

Data Index: 330451 (C4 (Web Text))

Max Activating Token Index: 943