Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5644 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.9603. Min Act: -0.0000

Data Index: 1267127 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.7485. Min Act: -0.0000

Data Index: 923941 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6126. Min Act: -0.0000

Data Index: 1173616 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6918. Min Act: -0.0000

Data Index: 224274 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.6830. Min Act: -0.0000

Data Index: 925824 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.5217. Min Act: -0.0000

Data Index: 1024775 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.5976. Min Act: -0.0000

Data Index: 770895 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.3927. Min Act: -0.0000

Data Index: 934936 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.4477. Min Act: -0.0000

Data Index: 434210 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.4761. Min Act: -0.0000

Data Index: 277004 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.5178. Min Act: -0.0000

Data Index: 819061 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.4203. Min Act: -0.0000

Data Index: 447216 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1056021 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.3836. Min Act: -0.0000

Data Index: 1491034 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.5786. Min Act: -0.0000

Data Index: 794791 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.4069. Min Act: -0.0000

Data Index: 649552 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1198010 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1432709 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.4015. Min Act: -0.0000

Data Index: 1208966 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 1.9603. Min Range: -1.9603

Max Act: 1.3030. Min Act: -0.0000

Data Index: 604830 (C4 (Web Text))

Max Activating Token Index: 232