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

Dataset: The Pile

Neuron 4116 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.9163. Min Act: -0.0000

Data Index: 749164 (The Pile)

Max Activating Token Index: 180

Text #1

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.1954. Min Act: -0.0000

Data Index: 932787 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.0784. Min Act: -0.0000

Data Index: 185085 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.1612. Min Act: -0.0000

Data Index: 231017 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1414579 (The Pile)

Max Activating Token Index: 527

Text #5

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.1068. Min Act: -0.0000

Data Index: 251851 (The Pile)

Max Activating Token Index: 680

Text #6

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.0932. Min Act: -0.0000

Data Index: 1940167 (The Pile)

Max Activating Token Index: 750

Text #7

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1767842 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1212423 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.0171. Min Act: -0.0000

Data Index: 452499 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1581954 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1526704 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 1.9163. Min Range: -1.9163

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1915293 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1932226 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1215121 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1529327 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1849637 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1945324 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1606108 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 1.9163. Min Range: -1.9163

Max Act: 0.7554. Min Act: -0.0000

Data Index: 921618 (The Pile)

Max Activating Token Index: 945