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

Dataset: The Pile

Neuron 1575 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1644387 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1958148 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8726. Min Act: -0.0000

Data Index: 843099 (The Pile)

Max Activating Token Index: 93

Text #3

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8734. Min Act: -0.0000

Data Index: 177306 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1508515 (The Pile)

Max Activating Token Index: 112

Text #5

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8202. Min Act: -0.0000

Data Index: 693130 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8406. Min Act: -0.0000

Data Index: 1217656 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8096. Min Act: -0.0000

Data Index: 1246639 (The Pile)

Max Activating Token Index: 72

Text #8

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7947. Min Act: -0.0000

Data Index: 1418866 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1838244 (The Pile)

Max Activating Token Index: 138

Text #10

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7248. Min Act: -0.0000

Data Index: 574574 (The Pile)

Max Activating Token Index: 17

Text #11

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1803641 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1588683 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7834. Min Act: -0.0000

Data Index: 1649796 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7983. Min Act: -0.0000

Data Index: 164518 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7809. Min Act: -0.0000

Data Index: 1135859 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.8011. Min Act: -0.0000

Data Index: 869870 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7911. Min Act: -0.0000

Data Index: 1822097 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1476252 (The Pile)

Max Activating Token Index: 358

Text #19

Max Range: 0.9227. Min Range: -0.9227

Max Act: 0.7175. Min Act: -0.0000

Data Index: 1917680 (The Pile)

Max Activating Token Index: 158