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

Dataset: The Pile

Neuron 2546 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: 0.3145. Min Range: -0.3145

Max Act: 0.3145. Min Act: -0.0000

Data Index: 734799 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2666. Min Act: -0.0000

Data Index: 889064 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2301. Min Act: -0.0000

Data Index: 700911 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1688565 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2157. Min Act: -0.0000

Data Index: 48002 (The Pile)

Max Activating Token Index: 620

Text #5

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1454765 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1996. Min Act: -0.0000

Data Index: 683613 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1893. Min Act: -0.0000

Data Index: 771217 (The Pile)

Max Activating Token Index: 219

Text #8

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1885. Min Act: -0.0000

Data Index: 277595 (The Pile)

Max Activating Token Index: 709

Text #9

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1974. Min Act: -0.0000

Data Index: 751827 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1922. Min Act: -0.0000

Data Index: 618555 (The Pile)

Max Activating Token Index: 424

Text #11

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1611. Min Act: -0.0000

Data Index: 1257321 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1786. Min Act: -0.0000

Data Index: 453224 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1716. Min Act: -0.0000

Data Index: 857421 (The Pile)

Max Activating Token Index: 663

Text #14

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1716. Min Act: -0.0000

Data Index: 213398 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1821. Min Act: -0.0000

Data Index: 70576 (The Pile)

Max Activating Token Index: 875

Text #16

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1696. Min Act: -0.0000

Data Index: 855135 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1580. Min Act: -0.0000

Data Index: 1410084 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1744745 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.3145. Min Range: -0.3145

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1788791 (The Pile)

Max Activating Token Index: 726