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

Dataset: The Pile

Neuron 1152 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4624. Min Act: -0.0000

Data Index: 747099 (The Pile)

Max Activating Token Index: 624

Text #1

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1573032 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1547147 (The Pile)

Max Activating Token Index: 623

Text #3

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4520. Min Act: -0.0000

Data Index: 298514 (The Pile)

Max Activating Token Index: 932

Text #4

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1599357 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4379. Min Act: -0.0000

Data Index: 1940462 (The Pile)

Max Activating Token Index: 74

Text #6

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4226. Min Act: -0.0000

Data Index: 1597630 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1843734 (The Pile)

Max Activating Token Index: 96

Text #8

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1942744 (The Pile)

Max Activating Token Index: 197

Text #9

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4011. Min Act: -0.0000

Data Index: 1236351 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3955. Min Act: -0.0000

Data Index: 234702 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1250608 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3935. Min Act: -0.0000

Data Index: 449683 (The Pile)

Max Activating Token Index: 977

Text #13

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1474296 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3876. Min Act: -0.0000

Data Index: 1675789 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1001592 (The Pile)

Max Activating Token Index: 785

Text #16

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3966. Min Act: -0.0000

Data Index: 696237 (The Pile)

Max Activating Token Index: 282

Text #17

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3959. Min Act: -0.0000

Data Index: 677805 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3974. Min Act: -0.0000

Data Index: 574057 (The Pile)

Max Activating Token Index: 817

Text #19

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1441645 (The Pile)

Max Activating Token Index: 565