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

Dataset: The Pile

Neuron 918 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1075814 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1215101 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1597217 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6324. Min Act: -0.0000

Data Index: 671566 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5809. Min Act: -0.0000

Data Index: 885613 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5764. Min Act: -0.0000

Data Index: 221227 (The Pile)

Max Activating Token Index: 641

Text #6

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1383698 (The Pile)

Max Activating Token Index: 791

Text #7

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1120136 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4850. Min Act: -0.0000

Data Index: 479082 (The Pile)

Max Activating Token Index: 733

Text #9

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1972471 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1456466 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1814647 (The Pile)

Max Activating Token Index: 352

Text #12

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1364409 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5349. Min Act: -0.0000

Data Index: 500948 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1932508 (The Pile)

Max Activating Token Index: 276

Text #15

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1147782 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5280. Min Act: -0.0000

Data Index: 789130 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1456837 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5012. Min Act: -0.0000

Data Index: 161930 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.6937. Min Range: -0.6937

Max Act: 0.5155. Min Act: -0.0000

Data Index: 747216 (The Pile)

Max Activating Token Index: 809