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

Dataset: The Pile

Neuron 3266 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: 1.2737. Min Range: -1.2737

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1026178 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 1.2737. Min Range: -1.2737

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1609080 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1672539 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.2737. Min Range: -1.2737

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1132868 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1199672 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 1.2737. Min Range: -1.2737

Max Act: 1.0119. Min Act: -0.0000

Data Index: 1549525 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1979963 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1421410 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.8641. Min Act: -0.0000

Data Index: 204589 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.9086. Min Act: -0.0000

Data Index: 1162141 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1908112 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1685990 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1346768 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.7928. Min Act: -0.0000

Data Index: 985802 (The Pile)

Max Activating Token Index: 264

Text #14

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1003521 (The Pile)

Max Activating Token Index: 358

Text #15

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1492011 (The Pile)

Max Activating Token Index: 580

Text #16

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.7741. Min Act: -0.0000

Data Index: 701455 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.5618. Min Act: -0.0000

Data Index: 1065194 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1311189 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.2737. Min Range: -1.2737

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1615478 (The Pile)

Max Activating Token Index: 334