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

Dataset: The Pile

Neuron 4206 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.6080. Min Act: -0.0000

Data Index: 1978007 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.5935. Min Act: -0.0000

Data Index: 1901734 (The Pile)

Max Activating Token Index: 361

Text #2

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.5183. Min Act: -0.0000

Data Index: 138135 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.5544. Min Act: -0.0000

Data Index: 443311 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.5449. Min Act: -0.0000

Data Index: 1993445 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.4138. Min Act: -0.0000

Data Index: 480405 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.4488. Min Act: -0.0000

Data Index: 719836 (The Pile)

Max Activating Token Index: 545

Text #7

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.4365. Min Act: -0.0000

Data Index: 808383 (The Pile)

Max Activating Token Index: 872

Text #8

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.3462. Min Act: -0.0000

Data Index: 49332 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2544. Min Act: -0.0000

Data Index: 300084 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1492565 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1950. Min Act: -0.0000

Data Index: 687873 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1944. Min Act: -0.0000

Data Index: 893780 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2696. Min Act: -0.0000

Data Index: 884432 (The Pile)

Max Activating Token Index: 942

Text #14

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2500. Min Act: -0.0000

Data Index: 248061 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1254395 (The Pile)

Max Activating Token Index: 911

Text #16

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2273. Min Act: -0.0000

Data Index: 1559367 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1917553 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.2834. Min Act: -0.0000

Data Index: 1722578 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 1.6080. Min Range: -1.6080

Max Act: 1.1251. Min Act: -0.0000

Data Index: 675034 (The Pile)

Max Activating Token Index: 218