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

Dataset: The Pile

Neuron 454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0795. Min Range: -1.0795

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1770976 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 1.0795. Min Range: -1.0795

Max Act: 1.0795. Min Act: -0.0000

Data Index: 762201 (The Pile)

Max Activating Token Index: 279

Text #2

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.9489. Min Act: -0.0000

Data Index: 790742 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.9829. Min Act: -0.0000

Data Index: 377548 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1053253 (The Pile)

Max Activating Token Index: 958

Text #5

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.9807. Min Act: -0.0000

Data Index: 632386 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1792319 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1840272 (The Pile)

Max Activating Token Index: 26

Text #8

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8246. Min Act: -0.0000

Data Index: 836078 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1783134 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8075. Min Act: -0.0000

Data Index: 595855 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8592. Min Act: -0.0000

Data Index: 215048 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1904482 (The Pile)

Max Activating Token Index: 425

Text #13

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8129. Min Act: -0.0000

Data Index: 354940 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1739839 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.7748. Min Act: -0.0000

Data Index: 586011 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.7650. Min Act: -0.0000

Data Index: 957092 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1995070 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.7549. Min Act: -0.0000

Data Index: 942073 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 1.0795. Min Range: -1.0795

Max Act: 0.7789. Min Act: -0.0000

Data Index: 378871 (The Pile)

Max Activating Token Index: 685