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

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

Neuron 330 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0002

Data Index: 120587 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0706. Min Act: -0.0002

Data Index: 107164 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0702. Min Act: -0.0002

Data Index: 795273 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1009949 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0681. Min Act: -0.0002

Data Index: 387348 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0704. Min Act: -0.0002

Data Index: 298988 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0688. Min Act: -0.0002

Data Index: 94904 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0665. Min Act: -0.0002

Data Index: 499489 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0670. Min Act: -0.0002

Data Index: 168477 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0705. Min Act: -0.0002

Data Index: 244902 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0693. Min Act: -0.0002

Data Index: 589821 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0695. Min Act: -0.0002

Data Index: 849626 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1265043 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0681. Min Act: -0.0002

Data Index: 690163 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0715. Min Act: -0.0002

Data Index: 7553 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0676. Min Act: -0.0002

Data Index: 174466 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0682. Min Act: -0.0002

Data Index: 921448 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1263811 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0653. Min Act: -0.0002

Data Index: 65388 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1106850 (C4 (Web Text))

Max Activating Token Index: 389