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

Dataset: The Pile

Neuron 1804 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: 1.3086. Min Range: -1.3086

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1730470 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.2089. Min Act: -0.0000

Data Index: 138958 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.3086. Min Act: -0.0000

Data Index: 1272993 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.1584. Min Act: -0.0000

Data Index: 571308 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0962. Min Act: -0.0000

Data Index: 314159 (The Pile)

Max Activating Token Index: 466

Text #5

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0995. Min Act: -0.0000

Data Index: 646727 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0494. Min Act: -0.0000

Data Index: 764568 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.1058. Min Act: -0.0000

Data Index: 314292 (The Pile)

Max Activating Token Index: 196

Text #8

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0607. Min Act: -0.0000

Data Index: 725572 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1635275 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1478230 (The Pile)

Max Activating Token Index: 37

Text #11

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1970746 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0291. Min Act: -0.0000

Data Index: 1979986 (The Pile)

Max Activating Token Index: 615

Text #13

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1123763 (The Pile)

Max Activating Token Index: 227

Text #14

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1120999 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9615. Min Act: -0.0000

Data Index: 495046 (The Pile)

Max Activating Token Index: 725

Text #16

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9586. Min Act: -0.0000

Data Index: 100578 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9533. Min Act: -0.0000

Data Index: 476947 (The Pile)

Max Activating Token Index: 81

Text #18

Max Range: 1.3086. Min Range: -1.3086

Max Act: 0.9870. Min Act: -0.0000

Data Index: 413034 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 1.3086. Min Range: -1.3086

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1355462 (The Pile)

Max Activating Token Index: 848