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

Dataset: The Pile

Neuron 2501 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: 2.3536. Min Range: -2.3536

Max Act: 2.3536. Min Act: -0.0000

Data Index: 1112929 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 2.3536. Min Range: -2.3536

Max Act: 2.1876. Min Act: -0.0000

Data Index: 262007 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 2.3536. Min Range: -2.3536

Max Act: 2.1315. Min Act: -0.0000

Data Index: 1535078 (The Pile)

Max Activating Token Index: 719

Text #3

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.9992. Min Act: -0.0000

Data Index: 314688 (The Pile)

Max Activating Token Index: 794

Text #4

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.8878. Min Act: -0.0000

Data Index: 1414902 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 2.3536. Min Range: -2.3536

Max Act: 2.0021. Min Act: -0.0000

Data Index: 350230 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.9683. Min Act: -0.0000

Data Index: 1265681 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7111. Min Act: -0.0000

Data Index: 854993 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.8668. Min Act: -0.0000

Data Index: 1348070 (The Pile)

Max Activating Token Index: 463

Text #9

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.5766. Min Act: -0.0000

Data Index: 859420 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.8215. Min Act: -0.0000

Data Index: 1838217 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.5348. Min Act: -0.0000

Data Index: 1032470 (The Pile)

Max Activating Token Index: 635

Text #12

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7994. Min Act: -0.0000

Data Index: 1055696 (The Pile)

Max Activating Token Index: 244

Text #13

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7068. Min Act: -0.0000

Data Index: 786487 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7921. Min Act: -0.0000

Data Index: 766022 (The Pile)

Max Activating Token Index: 856

Text #15

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7851. Min Act: -0.0000

Data Index: 1563175 (The Pile)

Max Activating Token Index: 97

Text #16

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7701. Min Act: -0.0000

Data Index: 1490854 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7620. Min Act: -0.0000

Data Index: 914281 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7836. Min Act: -0.0000

Data Index: 1008652 (The Pile)

Max Activating Token Index: 367

Text #19

Max Range: 2.3536. Min Range: -2.3536

Max Act: 1.7523. Min Act: -0.0000

Data Index: 1685656 (The Pile)

Max Activating Token Index: 213