Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1748 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0005

Data Index: 292980 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0798. Min Act: -0.0005

Data Index: 902998 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0748. Min Act: -0.0005

Data Index: 1319561 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0747. Min Act: -0.0005

Data Index: 556150 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0694. Min Act: -0.0005

Data Index: 1050266 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0736. Min Act: -0.0005

Data Index: 711774 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0729. Min Act: -0.0005

Data Index: 535684 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0720. Min Act: -0.0005

Data Index: 990863 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0695. Min Act: -0.0005

Data Index: 492293 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0686. Min Act: -0.0005

Data Index: 910154 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0686. Min Act: -0.0005

Data Index: 286780 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0677. Min Act: -0.0005

Data Index: 1303627 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0691. Min Act: -0.0005

Data Index: 316133 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0696. Min Act: -0.0005

Data Index: 1099079 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0687. Min Act: -0.0005

Data Index: 163548 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0681. Min Act: -0.0005

Data Index: 581886 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0696. Min Act: -0.0005

Data Index: 1200963 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0671. Min Act: -0.0005

Data Index: 395753 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0696. Min Act: -0.0005

Data Index: 593362 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0702. Min Act: -0.0005

Data Index: 55956 (C4 (Web Text))

Max Activating Token Index: 503