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

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

Neuron 3763 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1648992 (Python Code)

Max Activating Token Index: 662

Text #1

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3187. Min Act: -0.0001

Data Index: 1599265 (Python Code)

Max Activating Token Index: 807

Text #2

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3112. Min Act: -0.0001

Data Index: 604940 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2727. Min Act: -0.0001

Data Index: 817055 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2864. Min Act: -0.0001

Data Index: 598786 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3118. Min Act: -0.0001

Data Index: 696406 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2721. Min Act: -0.0001

Data Index: 125083 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2668. Min Act: -0.0001

Data Index: 501285 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3057. Min Act: -0.0001

Data Index: 1343799 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2827. Min Act: -0.0001

Data Index: 1287456 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2887. Min Act: -0.0001

Data Index: 918719 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2762. Min Act: -0.0001

Data Index: 1227938 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2793. Min Act: -0.0001

Data Index: 577809 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2889. Min Act: -0.0001

Data Index: 46387 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2937. Min Act: -0.0001

Data Index: 1173452 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2579. Min Act: -0.0001

Data Index: 943417 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2727. Min Act: -0.0001

Data Index: 886724 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2717. Min Act: -0.0001

Data Index: 968160 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.3098. Min Act: -0.0001

Data Index: 60672 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.3187. Min Range: -0.3187

Max Act: 0.2602. Min Act: -0.0001

Data Index: 36839 (C4 (Web Text))

Max Activating Token Index: 608