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

Dataset: The Pile

Neuron 7 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1241. Min Act: -0.0000

Data Index: 1373391 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1674903 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0965. Min Act: -0.0000

Data Index: 298174 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1236503 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1276967 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0990. Min Act: -0.0000

Data Index: 458996 (The Pile)

Max Activating Token Index: 992

Text #6

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0977. Min Act: -0.0000

Data Index: 723687 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0935. Min Act: -0.0000

Data Index: 600213 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1293033 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1304067 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0802. Min Act: -0.0000

Data Index: 344781 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1047736 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0819. Min Act: -0.0000

Data Index: 431800 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0905. Min Act: -0.0000

Data Index: 498002 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0903. Min Act: -0.0000

Data Index: 598896 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1358607 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0864. Min Act: -0.0000

Data Index: 873723 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0876. Min Act: -0.0000

Data Index: 175803 (The Pile)

Max Activating Token Index: 465

Text #18

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0772. Min Act: -0.0000

Data Index: 143519 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 0.1245. Min Range: -0.1245

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1183717 (The Pile)

Max Activating Token Index: 263