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

Dataset: The Pile

Neuron 2596 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: 1.4713. Min Range: -1.4713

Max Act: 1.4713. Min Act: -0.0000

Data Index: 1158103 (The Pile)

Max Activating Token Index: 518

Text #1

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1384622 (The Pile)

Max Activating Token Index: 250

Text #2

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.1852. Min Act: -0.0000

Data Index: 444520 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.1005. Min Act: -0.0000

Data Index: 33219 (The Pile)

Max Activating Token Index: 610

Text #4

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1834346 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.0510. Min Act: -0.0000

Data Index: 221277 (The Pile)

Max Activating Token Index: 524

Text #6

Max Range: 1.4713. Min Range: -1.4713

Max Act: 1.0779. Min Act: -0.0000

Data Index: 973055 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.9504. Min Act: -0.0000

Data Index: 72719 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1402597 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1648867 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8606. Min Act: -0.0000

Data Index: 757413 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1477449 (The Pile)

Max Activating Token Index: 656

Text #12

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1596127 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8129. Min Act: -0.0000

Data Index: 1894376 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8776. Min Act: -0.0000

Data Index: 724822 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.9235. Min Act: -0.0000

Data Index: 35590 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8199. Min Act: -0.0000

Data Index: 320800 (The Pile)

Max Activating Token Index: 75

Text #17

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1114103 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8308. Min Act: -0.0000

Data Index: 1619504 (The Pile)

Max Activating Token Index: 590

Text #19

Max Range: 1.4713. Min Range: -1.4713

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1566952 (The Pile)

Max Activating Token Index: 1008