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

Dataset: The Pile

Neuron 770 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.8504. Min Act: -0.0000

Data Index: 321217 (The Pile)

Max Activating Token Index: 396

Text #1

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1200810 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1431615 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6118. Min Act: -0.0000

Data Index: 615877 (The Pile)

Max Activating Token Index: 903

Text #4

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1916316 (The Pile)

Max Activating Token Index: 810

Text #5

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6180. Min Act: -0.0000

Data Index: 812369 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1734103 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5935. Min Act: 0.0000

Data Index: 595157 (The Pile)

Max Activating Token Index: 906

Text #8

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6584. Min Act: -0.0000

Data Index: 985106 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5421. Min Act: -0.0000

Data Index: 794241 (The Pile)

Max Activating Token Index: 986

Text #10

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1953402 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5809. Min Act: -0.0000

Data Index: 58467 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1864388 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5536. Min Act: -0.0000

Data Index: 653538 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5285. Min Act: -0.0000

Data Index: 775054 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.4796. Min Act: -0.0000

Data Index: 213932 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1514656 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.3991. Min Act: -0.0000

Data Index: 887573 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1154817 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 0.8504. Min Range: -0.8504

Max Act: 0.5059. Min Act: -0.0000

Data Index: 361939 (The Pile)

Max Activating Token Index: 803