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

Dataset: The Pile

Neuron 4269 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: 1.2052. Min Range: -1.2052

Max Act: 1.1849. Min Act: -0.0000

Data Index: 1490397 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.0802. Min Act: -0.0000

Data Index: 1187612 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.1599. Min Act: -0.0000

Data Index: 114089 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.1866. Min Act: -0.0000

Data Index: 583716 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.2052. Min Act: -0.0000

Data Index: 211630 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.0849. Min Act: -0.0000

Data Index: 303548 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 1.2052. Min Range: -1.2052

Max Act: 1.0823. Min Act: -0.0000

Data Index: 645002 (The Pile)

Max Activating Token Index: 978

Text #7

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1933800 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.9837. Min Act: -0.0000

Data Index: 685702 (The Pile)

Max Activating Token Index: 352

Text #9

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1651328 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.9509. Min Act: -0.0000

Data Index: 378414 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.9836. Min Act: -0.0000

Data Index: 344758 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.9739. Min Act: -0.0000

Data Index: 850320 (The Pile)

Max Activating Token Index: 635

Text #13

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.9010. Min Act: -0.0000

Data Index: 610904 (The Pile)

Max Activating Token Index: 197

Text #14

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8567. Min Act: -0.0000

Data Index: 921333 (The Pile)

Max Activating Token Index: 377

Text #15

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1882708 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.7726. Min Act: -0.0000

Data Index: 366692 (The Pile)

Max Activating Token Index: 877

Text #17

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1782476 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8697. Min Act: 0.0000

Data Index: 1020276 (The Pile)

Max Activating Token Index: 103

Text #19

Max Range: 1.2052. Min Range: -1.2052

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1651680 (The Pile)

Max Activating Token Index: 216