Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1702 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0721. Min Act: -0.0003

Data Index: 513541 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0003

Data Index: 1244686 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0665. Min Act: -0.0003

Data Index: 1127656 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1158635 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1228482 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0625. Min Act: -0.0003

Data Index: 891888 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0647. Min Act: -0.0003

Data Index: 814757 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0591. Min Act: -0.0003

Data Index: 214184 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0677. Min Act: -0.0003

Data Index: 958668 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0634. Min Act: -0.0003

Data Index: 662941 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0618. Min Act: -0.0003

Data Index: 487039 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1318990 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0608. Min Act: -0.0003

Data Index: 33326 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0605. Min Act: -0.0003

Data Index: 484349 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1272691 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1149169 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0622. Min Act: -0.0003

Data Index: 312724 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0598. Min Act: -0.0003

Data Index: 254066 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0595. Min Act: -0.0003

Data Index: 333287 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1087797 (C4 (Web Text))

Max Activating Token Index: 170