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

Dataset: The Pile

Neuron 951 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: 0.9000. Min Range: -0.9000

Max Act: 0.9000. Min Act: -0.0000

Data Index: 37748 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.8843. Min Act: -0.0000

Data Index: 1474256 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.8196. Min Act: -0.0000

Data Index: 87723 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1036514 (The Pile)

Max Activating Token Index: 134

Text #4

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.7126. Min Act: -0.0000

Data Index: 322172 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6992. Min Act: 0.0000

Data Index: 7097 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1379669 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6276. Min Act: 0.0000

Data Index: 1258000 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1632259 (The Pile)

Max Activating Token Index: 807

Text #9

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1281117 (The Pile)

Max Activating Token Index: 361

Text #10

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1642441 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6428. Min Act: -0.0000

Data Index: 647106 (The Pile)

Max Activating Token Index: 732

Text #12

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5991. Min Act: -0.0000

Data Index: 580673 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1271343 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.6009. Min Act: -0.0000

Data Index: 188069 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1027897 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1286969 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1847689 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1645519 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.9000. Min Range: -0.9000

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1999552 (The Pile)

Max Activating Token Index: 513