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

Dataset: The Pile

Neuron 3230 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: 3.7795. Min Range: -3.7795

Max Act: 3.7795. Min Act: -0.0000

Data Index: 1626282 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.2800. Min Act: -0.0000

Data Index: 1131834 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.5208. Min Act: -0.0000

Data Index: 1833444 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.4317. Min Act: -0.0000

Data Index: 383659 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.5862. Min Act: -0.0000

Data Index: 1459696 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.6718. Min Act: -0.0000

Data Index: 1025207 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.4928. Min Act: -0.0000

Data Index: 1941743 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.2045. Min Act: -0.0000

Data Index: 366120 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.3280. Min Act: -0.0000

Data Index: 571181 (The Pile)

Max Activating Token Index: 897

Text #9

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.3400. Min Act: -0.0000

Data Index: 671206 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.3044. Min Act: -0.0000

Data Index: 1182486 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.1657. Min Act: -0.0000

Data Index: 358115 (The Pile)

Max Activating Token Index: 769

Text #12

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.1651. Min Act: -0.0000

Data Index: 1918271 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.3155. Min Act: -0.0000

Data Index: 125231 (The Pile)

Max Activating Token Index: 366

Text #14

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.2948. Min Act: -0.0000

Data Index: 191629 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.4547. Min Act: -0.0000

Data Index: 1140477 (The Pile)

Max Activating Token Index: 892

Text #16

Max Range: 3.7795. Min Range: -3.7795

Max Act: 2.8079. Min Act: -0.0000

Data Index: 647919 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 3.7795. Min Range: -3.7795

Max Act: 2.9755. Min Act: -0.0000

Data Index: 1780769 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.5918. Min Act: -0.0000

Data Index: 1365897 (The Pile)

Max Activating Token Index: 214

Text #19

Max Range: 3.7795. Min Range: -3.7795

Max Act: 3.1363. Min Act: -0.0000

Data Index: 1910571 (The Pile)

Max Activating Token Index: 819