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

Dataset: The Pile

Neuron 2705 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: 1.0261. Min Range: -1.0261

Max Act: 0.9637. Min Act: 0.0000

Data Index: 988977 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 1.0261. Min Range: -1.0261

Max Act: 1.0261. Min Act: 0.0000

Data Index: 1360607 (The Pile)

Max Activating Token Index: 900

Text #2

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.8653. Min Act: 0.0000

Data Index: 1762635 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.8710. Min Act: -0.0000

Data Index: 211544 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1091889 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7745. Min Act: -0.0000

Data Index: 555203 (The Pile)

Max Activating Token Index: 826

Text #6

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7522. Min Act: -0.0000

Data Index: 552709 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7763. Min Act: -0.0000

Data Index: 700570 (The Pile)

Max Activating Token Index: 731

Text #8

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7522. Min Act: -0.0000

Data Index: 226941 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7703. Min Act: -0.0000

Data Index: 411934 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7643. Min Act: 0.0000

Data Index: 110097 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.8248. Min Act: -0.0000

Data Index: 135315 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7537. Min Act: -0.0000

Data Index: 798434 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1430757 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1084656 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1413678 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7225. Min Act: -0.0000

Data Index: 747300 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.6805. Min Act: -0.0000

Data Index: 143736 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1530606 (The Pile)

Max Activating Token Index: 85

Text #19

Max Range: 1.0261. Min Range: -1.0261

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1274362 (The Pile)

Max Activating Token Index: 704