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

Dataset: The Pile

Neuron 2797 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2405. Min Act: -0.0000

Data Index: 302097 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1577380 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1044427 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2318. Min Act: -0.0000

Data Index: 764548 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1972998 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1356248 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1519650 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1640. Min Act: -0.0000

Data Index: 78388 (The Pile)

Max Activating Token Index: 705

Text #8

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1114019 (The Pile)

Max Activating Token Index: 991

Text #9

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1862. Min Act: -0.0000

Data Index: 721365 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1680. Min Act: -0.0000

Data Index: 706891 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1665345 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1053264 (The Pile)

Max Activating Token Index: 96

Text #13

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1831848 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1811. Min Act: -0.0000

Data Index: 909895 (The Pile)

Max Activating Token Index: 810

Text #15

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1842. Min Act: -0.0000

Data Index: 794922 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1562. Min Act: -0.0000

Data Index: 581623 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1847389 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1708. Min Act: -0.0000

Data Index: 848137 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1874439 (The Pile)

Max Activating Token Index: 520