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

Dataset: The Pile

Neuron 2286 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.2033. Min Act: -0.0000

Data Index: 110643 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1980320 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1920. Min Act: -0.0000

Data Index: 1493367 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1389262 (The Pile)

Max Activating Token Index: 206

Text #4

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1716. Min Act: -0.0000

Data Index: 1398779 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1131571 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1201237 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1965. Min Act: -0.0000

Data Index: 263434 (The Pile)

Max Activating Token Index: 781

Text #8

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1604722 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1690. Min Act: -0.0000

Data Index: 69024 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1288578 (The Pile)

Max Activating Token Index: 921

Text #11

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1187065 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1674650 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1553361 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1617357 (The Pile)

Max Activating Token Index: 956

Text #15

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1734. Min Act: -0.0000

Data Index: 1191200 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1674. Min Act: -0.0000

Data Index: 573067 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1604866 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1642. Min Act: -0.0000

Data Index: 163918 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 0.2033. Min Range: -0.2033

Max Act: 0.1650. Min Act: -0.0000

Data Index: 1962987 (The Pile)

Max Activating Token Index: 820