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

Dataset: The Pile

Neuron 3116 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2887. Min Act: -0.0000

Data Index: 943040 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1803414 (The Pile)

Max Activating Token Index: 319

Text #2

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2650. Min Act: -0.0000

Data Index: 222154 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1775023 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1701859 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2581. Min Act: -0.0000

Data Index: 126028 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1310319 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1791079 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2270. Min Act: -0.0000

Data Index: 410529 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1525. Min Act: -0.0000

Data Index: 518900 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1285548 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1478394 (The Pile)

Max Activating Token Index: 709

Text #12

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2145. Min Act: -0.0000

Data Index: 33130 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2124. Min Act: -0.0000

Data Index: 760998 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1990. Min Act: -0.0000

Data Index: 774085 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1356506 (The Pile)

Max Activating Token Index: 286

Text #16

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1887319 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1043303 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1053905 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 0.2887. Min Range: -0.2887

Max Act: 0.2091. Min Act: -0.0000

Data Index: 485853 (The Pile)

Max Activating Token Index: 321