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

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

Neuron 553 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0757. Min Act: -0.0006

Data Index: 647561 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0753. Min Act: -0.0006

Data Index: 204472 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0743. Min Act: -0.0006

Data Index: 919709 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0719. Min Act: -0.0006

Data Index: 8937 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0704. Min Act: -0.0006

Data Index: 899261 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0700. Min Act: -0.0006

Data Index: 673397 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0637. Min Act: -0.0006

Data Index: 582371 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0636. Min Act: -0.0006

Data Index: 776661 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0679. Min Act: -0.0006

Data Index: 1331321 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0671. Min Act: -0.0006

Data Index: 272084 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0705. Min Act: -0.0006

Data Index: 869179 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0650. Min Act: -0.0006

Data Index: 1100563 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0650. Min Act: -0.0006

Data Index: 1035521 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0674. Min Act: -0.0006

Data Index: 860703 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0639. Min Act: -0.0006

Data Index: 1325085 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0669. Min Act: -0.0006

Data Index: 1250335 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0620. Min Act: -0.0006

Data Index: 914814 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0597. Min Act: -0.0006

Data Index: 218944 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0616. Min Act: -0.0006

Data Index: 598847 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0757. Min Range: -0.0757

Max Act: 0.0614. Min Act: -0.0006

Data Index: 60906 (C4 (Web Text))

Max Activating Token Index: 53