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

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

Neuron 3744 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0390. Min Range: -1.0390

Max Act: 1.0390. Min Act: -0.0000

Data Index: 702157 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.0390. Min Range: -1.0390

Max Act: 1.0150. Min Act: -0.0000

Data Index: 62178 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 1.0390. Min Range: -1.0390

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1235679 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.9352. Min Act: -0.0000

Data Index: 959016 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1207707 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8560. Min Act: -0.0000

Data Index: 1286391 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8782. Min Act: -0.0000

Data Index: 273972 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8598. Min Act: -0.0000

Data Index: 923551 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8238. Min Act: 0.0000

Data Index: 60168 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8662. Min Act: -0.0000

Data Index: 694513 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.8124. Min Act: -0.0000

Data Index: 44418 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7909. Min Act: -0.0000

Data Index: 890444 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7931. Min Act: -0.0000

Data Index: 183687 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7468. Min Act: -0.0000

Data Index: 91647 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7449. Min Act: -0.0000

Data Index: 576184 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7819. Min Act: -0.0000

Data Index: 1295419 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7101. Min Act: -0.0000

Data Index: 888049 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7309. Min Act: -0.0000

Data Index: 198068 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1134388 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 1.0390. Min Range: -1.0390

Max Act: 0.6992. Min Act: -0.0000

Data Index: 869080 (C4 (Web Text))

Max Activating Token Index: 807