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

Dataset: The Pile

Neuron 4975 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: 0.8022. Min Range: -0.8022

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1770596 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7255. Min Act: -0.0000

Data Index: 199485 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1484531 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1512980 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7681. Min Act: -0.0000

Data Index: 1849505 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1249081 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1823765 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.7296. Min Act: -0.0000

Data Index: 3104 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6597. Min Act: -0.0000

Data Index: 448945 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6595. Min Act: -0.0000

Data Index: 974834 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6753. Min Act: -0.0000

Data Index: 918632 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6951. Min Act: -0.0000

Data Index: 632598 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6335. Min Act: -0.0000

Data Index: 929863 (The Pile)

Max Activating Token Index: 875

Text #13

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1612864 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6306. Min Act: -0.0000

Data Index: 33266 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6058. Min Act: -0.0000

Data Index: 274774 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6475. Min Act: -0.0000

Data Index: 245843 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1456595 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6230. Min Act: -0.0000

Data Index: 321796 (The Pile)

Max Activating Token Index: 83

Text #19

Max Range: 0.8022. Min Range: -0.8022

Max Act: 0.6432. Min Act: -0.0000

Data Index: 928064 (The Pile)

Max Activating Token Index: 861