Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3345 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1543772 (Python Code)

Max Activating Token Index: 799

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0002

Data Index: 430518 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0670. Min Act: -0.0002

Data Index: 842163 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0649. Min Act: -0.0002

Data Index: 347967 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1342641 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0641. Min Act: -0.0002

Data Index: 737327 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1086029 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0632. Min Act: -0.0001

Data Index: 171275 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0656. Min Act: -0.0001

Data Index: 30565 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1024303 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1095876 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0637. Min Act: -0.0001

Data Index: 976095 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0597. Min Act: -0.0001

Data Index: 757373 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0623. Min Act: -0.0001

Data Index: 870825 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0598. Min Act: -0.0002

Data Index: 166480 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0617. Min Act: -0.0002

Data Index: 100199 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0567. Min Act: -0.0002

Data Index: 129350 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1254072 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1503048 (Python Code)

Max Activating Token Index: 619

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0650. Min Act: -0.0001

Data Index: 958049 (C4 (Web Text))

Max Activating Token Index: 564