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

Dataset: The Pile

Neuron 2628 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: 0.2676. Min Range: -0.2676

Max Act: 0.2676. Min Act: -0.0000

Data Index: 106831 (The Pile)

Max Activating Token Index: 225

Text #1

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1498824 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1278084 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2189. Min Act: -0.0000

Data Index: 1058179 (The Pile)

Max Activating Token Index: 47

Text #4

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2056. Min Act: -0.0000

Data Index: 815423 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1999. Min Act: -0.0000

Data Index: 82677 (The Pile)

Max Activating Token Index: 47

Text #6

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.2014. Min Act: -0.0000

Data Index: 876253 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1276556 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1895178 (The Pile)

Max Activating Token Index: 931

Text #9

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1749. Min Act: -0.0000

Data Index: 654571 (The Pile)

Max Activating Token Index: 432

Text #10

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1767. Min Act: -0.0000

Data Index: 467834 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1753. Min Act: -0.0000

Data Index: 685488 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1737. Min Act: -0.0000

Data Index: 650683 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1757. Min Act: -0.0000

Data Index: 30494 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1817. Min Act: -0.0000

Data Index: 976881 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1733. Min Act: -0.0000

Data Index: 986263 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1309574 (The Pile)

Max Activating Token Index: 479

Text #17

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1713. Min Act: -0.0000

Data Index: 990908 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1911875 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.2676. Min Range: -0.2676

Max Act: 0.1692. Min Act: -0.0000

Data Index: 454946 (The Pile)

Max Activating Token Index: 536