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

Dataset: The Pile

Neuron 301 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.5158. Min Act: -0.0000

Data Index: 1640077 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2599. Min Act: -0.0000

Data Index: 847217 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.3077. Min Act: -0.0000

Data Index: 870109 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1385933 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1969. Min Act: 0.0000

Data Index: 845123 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1019327 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1708. Min Act: -0.0000

Data Index: 9048 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0804. Min Act: 0.0000

Data Index: 1890112 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1005. Min Act: -0.0000

Data Index: 774813 (The Pile)

Max Activating Token Index: 115

Text #9

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0980. Min Act: -0.0000

Data Index: 925430 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0894. Min Act: -0.0000

Data Index: 1019807 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1260. Min Act: -0.0000

Data Index: 332764 (The Pile)

Max Activating Token Index: 954

Text #12

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1016. Min Act: -0.0000

Data Index: 640834 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1332226 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 1.5338. Min Range: -1.5338

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1822261 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.1015. Min Act: -0.0000

Data Index: 280927 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0227. Min Act: -0.0000

Data Index: 408139 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0197. Min Act: -0.0000

Data Index: 518260 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0548. Min Act: -0.0000

Data Index: 829826 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 1.5338. Min Range: -1.5338

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1275245 (The Pile)

Max Activating Token Index: 424