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

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

Neuron 3856 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: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1156836 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0606. Min Act: -0.0001

Data Index: 1154648 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0622. Min Act: -0.0001

Data Index: 916622 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0616. Min Act: -0.0002

Data Index: 659803 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0579. Min Act: -0.0001

Data Index: 214458 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0572. Min Act: -0.0002

Data Index: 613939 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0592. Min Act: -0.0002

Data Index: 229928 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0591. Min Act: -0.0002

Data Index: 320476 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1187597 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0594. Min Act: -0.0001

Data Index: 798094 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0544. Min Act: -0.0001

Data Index: 42024 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0545. Min Act: -0.0001

Data Index: 1224868 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0569. Min Act: -0.0001

Data Index: 676894 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1183955 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0537. Min Act: -0.0002

Data Index: 618465 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1076249 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0536. Min Act: -0.0001

Data Index: 276896 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1244755 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0535. Min Act: -0.0002

Data Index: 424486 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0553. Min Act: -0.0001

Data Index: 211887 (C4 (Web Text))

Max Activating Token Index: 351