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

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

Neuron 2731 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0001

Data Index: 382297 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1020826 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0858. Min Act: -0.0001

Data Index: 624976 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0905. Min Act: -0.0001

Data Index: 564030 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0897. Min Act: -0.0001

Data Index: 549073 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1246271 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0808. Min Act: -0.0001

Data Index: 923665 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0732. Min Act: -0.0001

Data Index: 688523 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0804. Min Act: -0.0001

Data Index: 518142 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1330151 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0684. Min Act: -0.0001

Data Index: 1229411 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0709. Min Act: -0.0001

Data Index: 999586 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0721. Min Act: -0.0001

Data Index: 82180 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0699. Min Act: -0.0001

Data Index: 924791 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1535469 (Python Code)

Max Activating Token Index: 954

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0687. Min Act: -0.0001

Data Index: 1113058 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1124465 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0658. Min Act: -0.0001

Data Index: 852240 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0676. Min Act: -0.0001

Data Index: 658358 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0703. Min Act: -0.0001

Data Index: 1522001 (Python Code)

Max Activating Token Index: 915