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

Dataset: The Pile

Neuron 1009 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.3578. Min Act: -0.0000

Data Index: 943375 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 1.3578. Min Range: -1.3578

Max Act: 1.0199. Min Act: -0.0000

Data Index: 201817 (The Pile)

Max Activating Token Index: 280

Text #2

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1388810 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7950. Min Act: -0.0000

Data Index: 193714 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7593. Min Act: -0.0000

Data Index: 874895 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1301256 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1420791 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7740. Min Act: -0.0000

Data Index: 1418117 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.7090. Min Act: -0.0000

Data Index: 123290 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1299953 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6667. Min Act: -0.0000

Data Index: 61617 (The Pile)

Max Activating Token Index: 845

Text #11

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1802790 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6504. Min Act: -0.0000

Data Index: 91661 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6886. Min Act: -0.0000

Data Index: 625912 (The Pile)

Max Activating Token Index: 888

Text #14

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6771. Min Act: -0.0000

Data Index: 1472808 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6331. Min Act: -0.0000

Data Index: 617906 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1488628 (The Pile)

Max Activating Token Index: 983

Text #17

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.5881. Min Act: -0.0000

Data Index: 829295 (The Pile)

Max Activating Token Index: 113

Text #18

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6008. Min Act: -0.0000

Data Index: 513116 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 1.3578. Min Range: -1.3578

Max Act: 0.6089. Min Act: -0.0000

Data Index: 341719 (The Pile)

Max Activating Token Index: 246