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

Dataset: The Pile

Neuron 3306 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.9003. Min Act: -0.0000

Data Index: 465086 (The Pile)

Max Activating Token Index: 721

Text #1

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1369744 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1682231 (The Pile)

Max Activating Token Index: 298

Text #3

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1589434 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1562525 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1208201 (The Pile)

Max Activating Token Index: 750

Text #6

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8963. Min Act: -0.0000

Data Index: 648321 (The Pile)

Max Activating Token Index: 199

Text #7

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8367. Min Act: -0.0000

Data Index: 1781491 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8361. Min Act: -0.0000

Data Index: 146677 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1394836 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8253. Min Act: -0.0000

Data Index: 206375 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1045602 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1473664 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7584. Min Act: -0.0000

Data Index: 360259 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8002. Min Act: -0.0000

Data Index: 1226271 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1763886 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1901385 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1571826 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7966. Min Act: -0.0000

Data Index: 569236 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 0.9422. Min Range: -0.9422

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1527376 (The Pile)

Max Activating Token Index: 678