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

Dataset: The Pile

Neuron 2230 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.6110. Min Act: -0.0000

Data Index: 1192520 (The Pile)

Max Activating Token Index: 441

Text #1

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.3227. Min Act: -0.0000

Data Index: 581128 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.3814. Min Act: -0.0000

Data Index: 594512 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.3187. Min Act: -0.0000

Data Index: 191298 (The Pile)

Max Activating Token Index: 69

Text #4

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1512569 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.2335. Min Act: -0.0000

Data Index: 41010 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1912. Min Act: -0.0000

Data Index: 725181 (The Pile)

Max Activating Token Index: 1001

Text #7

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1239080 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1553571 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.2144. Min Act: -0.0000

Data Index: 575641 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.2087. Min Act: -0.0000

Data Index: 1886594 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1799. Min Act: -0.0000

Data Index: 465178 (The Pile)

Max Activating Token Index: 562

Text #12

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1545. Min Act: -0.0000

Data Index: 216926 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1373911 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1813832 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1135093 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1941647 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1530666 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1755858 (The Pile)

Max Activating Token Index: 883

Text #19

Max Range: 1.6110. Min Range: -1.6110

Max Act: 1.1062. Min Act: -0.0000

Data Index: 1909424 (The Pile)

Max Activating Token Index: 787