Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2673 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.2365. Min Act: -0.0001

Data Index: 1036344 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.4687. Min Act: -0.0001

Data Index: 1026506 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3343. Min Act: -0.0001

Data Index: 1071897 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3771. Min Act: -0.0001

Data Index: 1243787 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3638. Min Act: -0.0001

Data Index: 973328 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3811. Min Act: -0.0001

Data Index: 637633 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.2421. Min Act: -0.0001

Data Index: 890872 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.2394. Min Act: -0.0001

Data Index: 114942 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.2653. Min Act: -0.0001

Data Index: 483107 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.1019. Min Act: -0.0001

Data Index: 546035 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.2471. Min Act: -0.0001

Data Index: 1121514 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.1365. Min Act: -0.0001

Data Index: 329249 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3778. Min Act: -0.0001

Data Index: 78199 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.2321. Min Act: -0.0001

Data Index: 461886 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.2782. Min Act: -0.0001

Data Index: 657324 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.1309. Min Act: -0.0001

Data Index: 1014856 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.3788. Min Act: -0.0001

Data Index: 1099858 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.1765. Min Act: -0.0001

Data Index: 634138 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.1997. Min Act: -0.0001

Data Index: 845486 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.4687. Min Range: -1.4687

Max Act: 1.1566. Min Act: -0.0001

Data Index: 944462 (C4 (Web Text))

Max Activating Token Index: 20