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

Dataset: The Pile

Neuron 2518 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7541. Min Act: -0.0000

Data Index: 820799 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7211. Min Act: 0.0000

Data Index: 347110 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1870779 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.6258. Min Act: -0.0000

Data Index: 782750 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1779157 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5528. Min Act: -0.0000

Data Index: 444920 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1847663 (The Pile)

Max Activating Token Index: 915

Text #7

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5887. Min Act: -0.0000

Data Index: 444936 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1485921 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5193. Min Act: -0.0000

Data Index: 335909 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1482416 (The Pile)

Max Activating Token Index: 903

Text #11

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1757072 (The Pile)

Max Activating Token Index: 42

Text #12

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4820. Min Act: -0.0000

Data Index: 138508 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1504416 (The Pile)

Max Activating Token Index: 626

Text #14

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1535817 (The Pile)

Max Activating Token Index: 707

Text #15

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.5243. Min Act: -0.0000

Data Index: 901096 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1835871 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1252461 (The Pile)

Max Activating Token Index: 674

Text #18

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4679. Min Act: -0.0000

Data Index: 867327 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 0.7541. Min Range: -0.7541

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1813183 (The Pile)

Max Activating Token Index: 792