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

Dataset: The Pile

Neuron 3587 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.6522. Min Act: -0.0000

Data Index: 612961 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.5449. Min Act: -0.0000

Data Index: 1577029 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3498. Min Act: -0.0000

Data Index: 940017 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.6024. Min Act: -0.0000

Data Index: 1524827 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.3181. Min Act: -0.0000

Data Index: 777552 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.2849. Min Act: -0.0000

Data Index: 253729 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1820. Min Act: -0.0000

Data Index: 1216267 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.1639. Min Act: -0.0000

Data Index: 1281116 (The Pile)

Max Activating Token Index: 85

Text #8

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.0077. Min Act: -0.0000

Data Index: 1495197 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.7647. Min Act: -0.0000

Data Index: 1563633 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 3.6522. Min Range: -3.6522

Max Act: 3.0501. Min Act: -0.0000

Data Index: 1624144 (The Pile)

Max Activating Token Index: 878

Text #11

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.8379. Min Act: -0.0000

Data Index: 1624754 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.8046. Min Act: -0.0000

Data Index: 1843034 (The Pile)

Max Activating Token Index: 308

Text #13

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.8791. Min Act: -0.0000

Data Index: 1817114 (The Pile)

Max Activating Token Index: 815

Text #14

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.8737. Min Act: -0.0000

Data Index: 1823479 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.6926. Min Act: -0.0000

Data Index: 1598814 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.7433. Min Act: -0.0000

Data Index: 154968 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.7040. Min Act: -0.0000

Data Index: 1536475 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.7000. Min Act: -0.0000

Data Index: 831286 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 3.6522. Min Range: -3.6522

Max Act: 2.6908. Min Act: -0.0000

Data Index: 345195 (The Pile)

Max Activating Token Index: 293