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

Dataset: The Pile

Neuron 1968 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: 0.8693. Min Range: -0.8693

Max Act: 0.8394. Min Act: -0.0000

Data Index: 972957 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8693. Min Act: -0.0000

Data Index: 1302541 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8318. Min Act: -0.0000

Data Index: 800254 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8401. Min Act: -0.0000

Data Index: 759907 (The Pile)

Max Activating Token Index: 115

Text #4

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.8071. Min Act: -0.0000

Data Index: 20688 (The Pile)

Max Activating Token Index: 30

Text #5

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7915. Min Act: -0.0000

Data Index: 745833 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1939531 (The Pile)

Max Activating Token Index: 566

Text #7

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7215. Min Act: -0.0000

Data Index: 690299 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.7634. Min Act: -0.0000

Data Index: 701797 (The Pile)

Max Activating Token Index: 748

Text #9

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6721. Min Act: -0.0000

Data Index: 218279 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6670. Min Act: -0.0000

Data Index: 699603 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1170114 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6322. Min Act: -0.0000

Data Index: 94297 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6447. Min Act: -0.0000

Data Index: 42365 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1260809 (The Pile)

Max Activating Token Index: 625

Text #15

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1520424 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6301. Min Act: -0.0000

Data Index: 172371 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6268. Min Act: -0.0000

Data Index: 642806 (The Pile)

Max Activating Token Index: 273

Text #18

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1229610 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 0.8693. Min Range: -0.8693

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1327263 (The Pile)

Max Activating Token Index: 165