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

Dataset: The Pile

Neuron 1982 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: 0.2556. Min Range: -0.2556

Max Act: 0.2426. Min Act: -0.0000

Data Index: 514235 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2556. Min Act: -0.0000

Data Index: 531127 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2328. Min Act: -0.0000

Data Index: 1221271 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2317. Min Act: -0.0000

Data Index: 21700 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2234. Min Act: -0.0000

Data Index: 394437 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1473695 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2098. Min Act: -0.0000

Data Index: 444628 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2083. Min Act: -0.0000

Data Index: 372292 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2138. Min Act: -0.0000

Data Index: 507592 (The Pile)

Max Activating Token Index: 929

Text #9

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1645884 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2054. Min Act: -0.0000

Data Index: 1300407 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1906. Min Act: -0.0000

Data Index: 188432 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1656. Min Act: -0.0000

Data Index: 826147 (The Pile)

Max Activating Token Index: 125

Text #13

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1585314 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1625838 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2059. Min Act: -0.0000

Data Index: 457943 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1803803 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1455746 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1858. Min Act: -0.0000

Data Index: 135515 (The Pile)

Max Activating Token Index: 847

Text #19

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2003. Min Act: -0.0000

Data Index: 526259 (The Pile)

Max Activating Token Index: 720