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

Dataset: The Pile

Neuron 1521 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1045157 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8501. Min Act: 0.0000

Data Index: 1021512 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7759. Min Act: -0.0000

Data Index: 124763 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8231. Min Act: -0.0000

Data Index: 354753 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6935. Min Act: -0.0000

Data Index: 917816 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1503049 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1491338 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8163. Min Act: 0.0000

Data Index: 801211 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8162. Min Act: -0.0000

Data Index: 1406704 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1572196 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1957987 (The Pile)

Max Activating Token Index: 1004

Text #11

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6867. Min Act: -0.0000

Data Index: 980802 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6898. Min Act: -0.0000

Data Index: 511047 (The Pile)

Max Activating Token Index: 914

Text #13

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7481. Min Act: -0.0000

Data Index: 155483 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6357. Min Act: -0.0000

Data Index: 805851 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6442. Min Act: 0.0000

Data Index: 197834 (The Pile)

Max Activating Token Index: 912

Text #16

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1608237 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1479872 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1612096 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6135. Min Act: -0.0000

Data Index: 565612 (The Pile)

Max Activating Token Index: 426