Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2103 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1126647 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.2233. Min Act: -0.0000

Data Index: 1722132 (The Pile)

Max Activating Token Index: 232

Text #2

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1991868 (The Pile)

Max Activating Token Index: 301

Text #3

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.0094. Min Act: -0.0000

Data Index: 426073 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1455589 (The Pile)

Max Activating Token Index: 252

Text #5

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1658764 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1596907 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1019786 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 1.2826. Min Range: -1.2826

Max Act: 1.0246. Min Act: -0.0000

Data Index: 688242 (The Pile)

Max Activating Token Index: 726

Text #9

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8978. Min Act: -0.0000

Data Index: 410835 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1406074 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1689285 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8215. Min Act: -0.0000

Data Index: 634756 (The Pile)

Max Activating Token Index: 812

Text #13

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9460. Min Act: -0.0000

Data Index: 276895 (The Pile)

Max Activating Token Index: 274

Text #14

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.9677. Min Act: -0.0000

Data Index: 1883924 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8653. Min Act: -0.0000

Data Index: 825307 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8384. Min Act: -0.0000

Data Index: 623519 (The Pile)

Max Activating Token Index: 84

Text #17

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8417. Min Act: -0.0000

Data Index: 245780 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8806. Min Act: -0.0000

Data Index: 95966 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 1.2826. Min Range: -1.2826

Max Act: 0.8306. Min Act: -0.0000

Data Index: 125842 (The Pile)

Max Activating Token Index: 517