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

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

Neuron 1244 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: 0.0692. Min Range: -0.0692

Max Act: 0.0692. Min Act: -0.0001

Data Index: 292499 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0653. Min Act: -0.0001

Data Index: 1320488 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0663. Min Act: -0.0001

Data Index: 769675 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0654. Min Act: -0.0001

Data Index: 390460 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1058607 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0626. Min Act: -0.0001

Data Index: 834756 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1514565 (Python Code)

Max Activating Token Index: 261

Text #7

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0642. Min Act: -0.0001

Data Index: 122520 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0643. Min Act: -0.0001

Data Index: 1277121 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0628. Min Act: -0.0001

Data Index: 835041 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0622. Min Act: -0.0001

Data Index: 116215 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0600. Min Act: -0.0001

Data Index: 423570 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0634. Min Act: -0.0001

Data Index: 768715 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1294732 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1229917 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1017543 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1210745 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0609. Min Act: -0.0001

Data Index: 444351 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1649836 (Python Code)

Max Activating Token Index: 63

Text #19

Max Range: 0.0692. Min Range: -0.0692

Max Act: 0.0560. Min Act: -0.0001

Data Index: 796024 (C4 (Web Text))

Max Activating Token Index: 454