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

Dataset: The Pile

Neuron 3975 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: 5.8039. Min Range: -5.8039

Max Act: 5.8039. Min Act: -0.0000

Data Index: 898598 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 5.8039. Min Range: -5.8039

Max Act: 4.5615. Min Act: -0.0000

Data Index: 1812805 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 5.8039. Min Range: -5.8039

Max Act: 4.3058. Min Act: -0.0000

Data Index: 434572 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 5.8039. Min Range: -5.8039

Max Act: 4.2283. Min Act: -0.0000

Data Index: 1367155 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.7988. Min Act: -0.0000

Data Index: 807949 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.9552. Min Act: -0.0000

Data Index: 794668 (The Pile)

Max Activating Token Index: 216

Text #6

Max Range: 5.8039. Min Range: -5.8039

Max Act: 4.0427. Min Act: -0.0000

Data Index: 1817456 (The Pile)

Max Activating Token Index: 220

Text #7

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.2545. Min Act: -0.0000

Data Index: 71943 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 5.8039. Min Range: -5.8039

Max Act: 4.0083. Min Act: -0.0000

Data Index: 49627 (The Pile)

Max Activating Token Index: 497

Text #9

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.7873. Min Act: -0.0000

Data Index: 1186344 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.5426. Min Act: -0.0000

Data Index: 1647393 (The Pile)

Max Activating Token Index: 426

Text #11

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.7947. Min Act: -0.0000

Data Index: 391289 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.4871. Min Act: -0.0000

Data Index: 1388961 (The Pile)

Max Activating Token Index: 308

Text #13

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.5825. Min Act: -0.0000

Data Index: 923373 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.7081. Min Act: -0.0000

Data Index: 825365 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.4476. Min Act: -0.0000

Data Index: 1676178 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.5751. Min Act: -0.0000

Data Index: 1127964 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.2010. Min Act: -0.0000

Data Index: 1211207 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.1532. Min Act: -0.0000

Data Index: 1940493 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 5.8039. Min Range: -5.8039

Max Act: 3.5587. Min Act: -0.0000

Data Index: 877592 (The Pile)

Max Activating Token Index: 470