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

Dataset: The Pile

Neuron 2101 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: 1.1712. Min Range: -1.1712

Max Act: 1.0911. Min Act: -0.0000

Data Index: 1619925 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.1712. Min Act: -0.0000

Data Index: 132571 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.1034. Min Act: -0.0000

Data Index: 158480 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.0598. Min Act: -0.0000

Data Index: 642234 (The Pile)

Max Activating Token Index: 285

Text #4

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.0131. Min Act: -0.0000

Data Index: 296653 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1121790 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1232694 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1867508 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9484. Min Act: -0.0000

Data Index: 256737 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9649. Min Act: -0.0000

Data Index: 886313 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8761. Min Act: -0.0000

Data Index: 392905 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1039219 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9473. Min Act: -0.0000

Data Index: 559845 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1012779 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8787. Min Act: -0.0000

Data Index: 273471 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8163. Min Act: -0.0000

Data Index: 123134 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1610645 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1386216 (The Pile)

Max Activating Token Index: 93

Text #18

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8497. Min Act: -0.0000

Data Index: 650174 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7887. Min Act: -0.0000

Data Index: 926690 (The Pile)

Max Activating Token Index: 594