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

Dataset: The Pile

Neuron 4758 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.4865. Min Act: -0.0000

Data Index: 1149590 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.4482. Min Act: -0.0000

Data Index: 661353 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.4303. Min Act: -0.0000

Data Index: 615573 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.3525. Min Act: -0.0000

Data Index: 1913233 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.2077. Min Act: -0.0000

Data Index: 1240329 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.3387. Min Act: -0.0000

Data Index: 153904 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.3087. Min Act: -0.0000

Data Index: 497947 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.4006. Min Act: -0.0000

Data Index: 671717 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.2607. Min Act: -0.0000

Data Index: 954775 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.4402. Min Act: -0.0000

Data Index: 322730 (The Pile)

Max Activating Token Index: 775

Text #10

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.4068. Min Act: -0.0000

Data Index: 1712656 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.2160. Min Act: -0.0000

Data Index: 981189 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.2189. Min Act: -0.0000

Data Index: 233165 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.0603. Min Act: -0.0000

Data Index: 492660 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.2074. Min Act: -0.0000

Data Index: 322623 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.3493. Min Act: -0.0000

Data Index: 1555456 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.1568. Min Act: -0.0000

Data Index: 517262 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 3.4865. Min Range: -3.4865

Max Act: 2.7349. Min Act: -0.0000

Data Index: 630124 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 3.4865. Min Range: -3.4865

Max Act: 3.0914. Min Act: -0.0000

Data Index: 435498 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 3.4865. Min Range: -3.4865

Max Act: 2.9191. Min Act: -0.0000

Data Index: 1550732 (The Pile)

Max Activating Token Index: 305