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

Dataset: The Pile

Neuron 2963 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: 1.5279. Min Range: -1.5279

Max Act: 1.5102. Min Act: -0.0000

Data Index: 397994 (The Pile)

Max Activating Token Index: 532

Text #1

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1887042 (The Pile)

Max Activating Token Index: 762

Text #2

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1005088 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.3771. Min Act: -0.0000

Data Index: 199785 (The Pile)

Max Activating Token Index: 120

Text #4

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1952848 (The Pile)

Max Activating Token Index: 376

Text #5

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.3090. Min Act: -0.0000

Data Index: 163252 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.2576. Min Act: -0.0000

Data Index: 1886191 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1988501 (The Pile)

Max Activating Token Index: 487

Text #8

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.2378. Min Act: -0.0000

Data Index: 1389487 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1033. Min Act: -0.0000

Data Index: 1545529 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.0745. Min Act: -0.0000

Data Index: 877085 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.0789. Min Act: -0.0000

Data Index: 407360 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1515645 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1438. Min Act: -0.0000

Data Index: 350119 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1919381 (The Pile)

Max Activating Token Index: 215

Text #15

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.0875. Min Act: -0.0000

Data Index: 849990 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1762. Min Act: -0.0000

Data Index: 1270981 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1880711 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.1773. Min Act: -0.0000

Data Index: 921031 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 1.5279. Min Range: -1.5279

Max Act: 1.0821. Min Act: -0.0000

Data Index: 144731 (The Pile)

Max Activating Token Index: 428