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

Dataset: The Pile

Neuron 1045 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: 1.6262. Min Range: -1.6262

Max Act: 1.6262. Min Act: -0.0000

Data Index: 587029 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1081894 (The Pile)

Max Activating Token Index: 863

Text #2

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.1797. Min Act: -0.0000

Data Index: 611269 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1889752 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.2621. Min Act: -0.0000

Data Index: 370640 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1919401 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1828806 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1987178 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.8457. Min Act: -0.0000

Data Index: 1914032 (The Pile)

Max Activating Token Index: 666

Text #9

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1849737 (The Pile)

Max Activating Token Index: 517

Text #10

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9903. Min Act: -0.0000

Data Index: 1550605 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1019092 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 1.6262. Min Range: -1.6262

Max Act: 1.0145. Min Act: -0.0000

Data Index: 754959 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.8877. Min Act: -0.0000

Data Index: 1500704 (The Pile)

Max Activating Token Index: 618

Text #14

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1647806 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.7135. Min Act: -0.0000

Data Index: 225717 (The Pile)

Max Activating Token Index: 918

Text #16

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.8128. Min Act: -0.0000

Data Index: 633902 (The Pile)

Max Activating Token Index: 945

Text #17

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1032326 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1422041 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 1.6262. Min Range: -1.6262

Max Act: 0.8338. Min Act: -0.0001

Data Index: 1852913 (The Pile)

Max Activating Token Index: 702