Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1348 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.5706. Min Act: -0.0000

Data Index: 1096114 (The Pile)

Max Activating Token Index: 63

Text #1

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.3700. Min Act: -0.0000

Data Index: 313951 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1445361 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.4327. Min Act: -0.0000

Data Index: 1839983 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1832581 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.3254. Min Act: -0.0000

Data Index: 1378982 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1829673 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.2583. Min Act: -0.0000

Data Index: 358651 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1348989 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.3312. Min Act: -0.0000

Data Index: 1816528 (The Pile)

Max Activating Token Index: 988

Text #10

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.2148. Min Act: -0.0000

Data Index: 1565368 (The Pile)

Max Activating Token Index: 70

Text #11

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1732238 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.1706. Min Act: -0.0000

Data Index: 264890 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1677851 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1619903 (The Pile)

Max Activating Token Index: 826

Text #15

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1903997 (The Pile)

Max Activating Token Index: 906

Text #16

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.0713. Min Act: -0.0000

Data Index: 17138 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.1613. Min Act: -0.0000

Data Index: 660322 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1203194 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 1.5706. Min Range: -1.5706

Max Act: 1.0278. Min Act: -0.0000

Data Index: 273795 (The Pile)

Max Activating Token Index: 61