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

Dataset: The Pile

Neuron 2479 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.7929. Min Act: -0.0000

Data Index: 526095 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.7688. Min Act: 0.0000

Data Index: 1174236 (The Pile)

Max Activating Token Index: 567

Text #2

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.6072. Min Act: -0.0000

Data Index: 615457 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1228714 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1509799 (The Pile)

Max Activating Token Index: 516

Text #5

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.3795. Min Act: -0.0000

Data Index: 1339600 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.5084. Min Act: -0.0000

Data Index: 1965655 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.4304. Min Act: -0.0000

Data Index: 358882 (The Pile)

Max Activating Token Index: 772

Text #8

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.3790. Min Act: -0.0000

Data Index: 1270326 (The Pile)

Max Activating Token Index: 417

Text #9

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.3950. Min Act: -0.0000

Data Index: 1362161 (The Pile)

Max Activating Token Index: 518

Text #10

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1769346 (The Pile)

Max Activating Token Index: 368

Text #11

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.4408. Min Act: -0.0000

Data Index: 1053905 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.2695. Min Act: -0.0000

Data Index: 811290 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.4384. Min Act: -0.0000

Data Index: 1066657 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.3634. Min Act: -0.0000

Data Index: 1132161 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.1654. Min Act: -0.0000

Data Index: 882304 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.3432. Min Act: -0.0000

Data Index: 344377 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.1117. Min Act: -0.0000

Data Index: 1158915 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.0249. Min Act: -0.0000

Data Index: 561602 (The Pile)

Max Activating Token Index: 773

Text #19

Max Range: 1.7929. Min Range: -1.7929

Max Act: 1.1755. Min Act: -0.0000

Data Index: 810145 (The Pile)

Max Activating Token Index: 901