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

Dataset: The Pile

Neuron 1159 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1850313 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1825294 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2097. Min Act: 0.0001

Data Index: 501049 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2048. Min Act: 0.0000

Data Index: 1139181 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1806570 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1697523 (The Pile)

Max Activating Token Index: 995

Text #6

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1572327 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1026272 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1790. Min Act: 0.0002

Data Index: 191765 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1815. Min Act: -0.0000

Data Index: 582673 (The Pile)

Max Activating Token Index: 283

Text #10

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1923376 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1129798 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1471528 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1643. Min Act: -0.0000

Data Index: 296499 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1460298 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1758819 (The Pile)

Max Activating Token Index: 816

Text #16

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1801. Min Act: 0.0000

Data Index: 522841 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1646. Min Act: -0.0000

Data Index: 653772 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1731. Min Act: -0.0000

Data Index: 214698 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1632. Min Act: -0.0000

Data Index: 390661 (The Pile)

Max Activating Token Index: 1014