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

Dataset: The Pile

Neuron 2856 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.8636. Min Act: -0.0000

Data Index: 163178 (The Pile)

Max Activating Token Index: 310

Text #1

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.6328. Min Act: -0.0000

Data Index: 1361432 (The Pile)

Max Activating Token Index: 43

Text #2

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.5126. Min Act: -0.0000

Data Index: 1350779 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.5702. Min Act: -0.0000

Data Index: 807545 (The Pile)

Max Activating Token Index: 817

Text #4

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.3596. Min Act: -0.0000

Data Index: 651830 (The Pile)

Max Activating Token Index: 851

Text #5

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.4477. Min Act: -0.0000

Data Index: 972774 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.3617. Min Act: -0.0000

Data Index: 1854077 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.4316. Min Act: -0.0000

Data Index: 1388758 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.3285. Min Act: -0.0000

Data Index: 1790901 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.2010. Min Act: -0.0000

Data Index: 1554652 (The Pile)

Max Activating Token Index: 917

Text #10

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1845256 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.2035. Min Act: -0.0000

Data Index: 413366 (The Pile)

Max Activating Token Index: 294

Text #12

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.1223. Min Act: -0.0000

Data Index: 1187561 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.2195. Min Act: -0.0000

Data Index: 1792083 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1349328 (The Pile)

Max Activating Token Index: 424

Text #15

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.1875. Min Act: -0.0000

Data Index: 748776 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1381760 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.2767. Min Act: -0.0000

Data Index: 164474 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1187412 (The Pile)

Max Activating Token Index: 249

Text #19

Max Range: 1.8636. Min Range: -1.8636

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1453408 (The Pile)

Max Activating Token Index: 149