Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0650. Min Act: -0.0002

Data Index: 41041 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0663. Min Act: -0.0002

Data Index: 662139 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0648. Min Act: -0.0002

Data Index: 566160 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0666. Min Act: -0.0003

Data Index: 953725 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0656. Min Act: -0.0002

Data Index: 418096 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0642. Min Act: -0.0003

Data Index: 1227258 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0661. Min Act: -0.0002

Data Index: 322261 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1188153 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1246128 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0614. Min Act: -0.0002

Data Index: 145479 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1119503 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1316188 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0594. Min Act: -0.0002

Data Index: 682849 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0583. Min Act: -0.0003

Data Index: 250445 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0582. Min Act: -0.0003

Data Index: 92507 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0597. Min Act: -0.0002

Data Index: 31714 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0590. Min Act: -0.0001

Data Index: 1326235 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0581. Min Act: -0.0001

Data Index: 80805 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0562. Min Act: -0.0003

Data Index: 546222 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.0666. Min Range: -0.0666

Max Act: 0.0565. Min Act: -0.0004

Data Index: 1309364 (C4 (Web Text))

Max Activating Token Index: 632