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

Dataset: The Pile

Neuron 781 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: 0.4277. Min Range: -0.4277

Max Act: 0.4277. Min Act: -0.0000

Data Index: 993739 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3073. Min Act: -0.0000

Data Index: 108836 (The Pile)

Max Activating Token Index: 603

Text #2

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1135916 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1644596 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2603. Min Act: -0.0000

Data Index: 175957 (The Pile)

Max Activating Token Index: 599

Text #5

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2976. Min Act: -0.0000

Data Index: 961813 (The Pile)

Max Activating Token Index: 931

Text #6

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2915. Min Act: -0.0000

Data Index: 415990 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2502. Min Act: -0.0000

Data Index: 1324591 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2711. Min Act: -0.0000

Data Index: 590710 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2888. Min Act: -0.0000

Data Index: 809665 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2830. Min Act: -0.0000

Data Index: 187838 (The Pile)

Max Activating Token Index: 385

Text #11

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1538032 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2777. Min Act: -0.0000

Data Index: 58322 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2871. Min Act: -0.0000

Data Index: 352159 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2670. Min Act: -0.0000

Data Index: 636662 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1013456 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1864349 (The Pile)

Max Activating Token Index: 907

Text #17

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2610. Min Act: -0.0000

Data Index: 311722 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2670. Min Act: -0.0000

Data Index: 258572 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.4277. Min Range: -0.4277

Max Act: 0.2722. Min Act: -0.0000

Data Index: 95774 (The Pile)

Max Activating Token Index: 370