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

Dataset: The Pile

Neuron 2862 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2029. Min Act: -0.0000

Data Index: 507083 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2060. Min Act: -0.0000

Data Index: 627239 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1161896 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1745. Min Act: -0.0000

Data Index: 807631 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1360500 (The Pile)

Max Activating Token Index: 512

Text #5

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1654137 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1065846 (The Pile)

Max Activating Token Index: 98

Text #7

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1839. Min Act: -0.0000

Data Index: 687033 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2102. Min Act: -0.0000

Data Index: 909486 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1931. Min Act: -0.0000

Data Index: 664396 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1824622 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1651466 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1536990 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1528347 (The Pile)

Max Activating Token Index: 30

Text #14

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1918. Min Act: -0.0000

Data Index: 1286873 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1690. Min Act: -0.0000

Data Index: 226198 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1601503 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1650. Min Act: -0.0000

Data Index: 438317 (The Pile)

Max Activating Token Index: 347

Text #18

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1988724 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1097409 (The Pile)

Max Activating Token Index: 814