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

Dataset: The Pile

Neuron 1146 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: 0.2413. Min Range: -0.2413

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1917713 (The Pile)

Max Activating Token Index: 784

Text #1

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2344. Min Act: -0.0000

Data Index: 894852 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2412. Min Act: -0.0000

Data Index: 836861 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1578540 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2146. Min Act: -0.0000

Data Index: 929484 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2295. Min Act: -0.0000

Data Index: 890130 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1165191 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1519853 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2184. Min Act: -0.0000

Data Index: 358682 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1907. Min Act: -0.0000

Data Index: 250722 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1827790 (The Pile)

Max Activating Token Index: 957

Text #11

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2068. Min Act: -0.0000

Data Index: 61761 (The Pile)

Max Activating Token Index: 892

Text #12

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1173262 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1984. Min Act: -0.0000

Data Index: 565535 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.2007. Min Act: -0.0000

Data Index: 756874 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1830. Min Act: -0.0000

Data Index: 883886 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1870. Min Act: -0.0000

Data Index: 215979 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1971. Min Act: -0.0000

Data Index: 1758667 (The Pile)

Max Activating Token Index: 464

Text #18

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1166937 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 0.2413. Min Range: -0.2413

Max Act: 0.1997. Min Act: -0.0000

Data Index: 626726 (The Pile)

Max Activating Token Index: 428