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

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

Neuron 3436 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3827. Min Act: 0.0000

Data Index: 386296 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3442. Min Act: -0.0001

Data Index: 677522 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3211. Min Act: -0.0000

Data Index: 556678 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.3078. Min Act: -0.0001

Data Index: 729264 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2953. Min Act: 0.0000

Data Index: 54871 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1133735 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2833. Min Act: -0.0000

Data Index: 8127 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2755. Min Act: -0.0000

Data Index: 778427 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2584. Min Act: 0.0000

Data Index: 106139 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2740. Min Act: -0.0000

Data Index: 655116 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2735. Min Act: 0.0000

Data Index: 492163 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2649. Min Act: -0.0001

Data Index: 128301 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2623. Min Act: 0.0000

Data Index: 1277097 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2696. Min Act: 0.0000

Data Index: 743371 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2749. Min Act: 0.0000

Data Index: 695385 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1207517 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2720. Min Act: 0.0000

Data Index: 1046435 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2544. Min Act: -0.0001

Data Index: 274625 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1251294 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.3827. Min Range: -0.3827

Max Act: 0.2607. Min Act: 0.0000

Data Index: 784579 (C4 (Web Text))

Max Activating Token Index: 7