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

Dataset: The Pile

Neuron 3113 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1637668 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1066856 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3432. Min Act: -0.0000

Data Index: 1347707 (The Pile)

Max Activating Token Index: 871

Text #3

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1951886 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1747275 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2875. Min Act: -0.0000

Data Index: 998069 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1664102 (The Pile)

Max Activating Token Index: 183

Text #7

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1195041 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1319485 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1791139 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1231039 (The Pile)

Max Activating Token Index: 228

Text #11

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1189566 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2717. Min Act: -0.0000

Data Index: 1164999 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2678. Min Act: -0.0000

Data Index: 1456001 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1788813 (The Pile)

Max Activating Token Index: 717

Text #15

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2705. Min Act: -0.0000

Data Index: 14286 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2492. Min Act: -0.0000

Data Index: 693848 (The Pile)

Max Activating Token Index: 52

Text #17

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2258. Min Act: -0.0000

Data Index: 354811 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1825313 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.4713. Min Range: -0.4713

Max Act: 0.2245. Min Act: -0.0000

Data Index: 752614 (The Pile)

Max Activating Token Index: 443