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

Dataset: The Pile

Neuron 1706 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: 1.0198. Min Range: -1.0198

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1369082 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.9886. Min Act: -0.0000

Data Index: 767966 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8562. Min Act: -0.0000

Data Index: 373931 (The Pile)

Max Activating Token Index: 234

Text #3

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7881. Min Act: -0.0000

Data Index: 674175 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8118. Min Act: -0.0000

Data Index: 173564 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8237. Min Act: -0.0000

Data Index: 1205866 (The Pile)

Max Activating Token Index: 478

Text #6

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1038060 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8026. Min Act: -0.0000

Data Index: 406093 (The Pile)

Max Activating Token Index: 36

Text #8

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8435. Min Act: -0.0000

Data Index: 996560 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1266285 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1637153 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8033. Min Act: -0.0000

Data Index: 307416 (The Pile)

Max Activating Token Index: 375

Text #12

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7751. Min Act: -0.0000

Data Index: 27619 (The Pile)

Max Activating Token Index: 206

Text #13

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1195140 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1558829 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.8335. Min Act: 0.0000

Data Index: 1610464 (The Pile)

Max Activating Token Index: 901

Text #16

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7610. Min Act: -0.0000

Data Index: 760873 (The Pile)

Max Activating Token Index: 404

Text #17

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7827. Min Act: -0.0000

Data Index: 72747 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7555. Min Act: -0.0000

Data Index: 485884 (The Pile)

Max Activating Token Index: 375

Text #19

Max Range: 1.0198. Min Range: -1.0198

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1744658 (The Pile)

Max Activating Token Index: 23