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

Dataset: The Pile

Neuron 4062 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: 1.7890. Min Range: -1.7890

Max Act: 1.7890. Min Act: -0.0000

Data Index: 284011 (The Pile)

Max Activating Token Index: 871

Text #1

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.3618. Min Act: -0.0000

Data Index: 683962 (The Pile)

Max Activating Token Index: 328

Text #2

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.2765. Min Act: -0.0000

Data Index: 584235 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1159785 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1842303 (The Pile)

Max Activating Token Index: 938

Text #5

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.2537. Min Act: -0.0000

Data Index: 941753 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.2942. Min Act: -0.0000

Data Index: 1956888 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1646516 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1486. Min Act: -0.0000

Data Index: 553698 (The Pile)

Max Activating Token Index: 333

Text #9

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1844062 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1728. Min Act: -0.0000

Data Index: 478950 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1565. Min Act: -0.0000

Data Index: 377263 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1219. Min Act: -0.0000

Data Index: 319221 (The Pile)

Max Activating Token Index: 559

Text #13

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1252. Min Act: -0.0000

Data Index: 1408417 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1880. Min Act: -0.0000

Data Index: 1874135 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.0982. Min Act: -0.0000

Data Index: 1569603 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1079. Min Act: -0.0000

Data Index: 1367575 (The Pile)

Max Activating Token Index: 306

Text #17

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1447. Min Act: -0.0000

Data Index: 726900 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.0679. Min Act: -0.0000

Data Index: 397682 (The Pile)

Max Activating Token Index: 984

Text #19

Max Range: 1.7890. Min Range: -1.7890

Max Act: 1.1678. Min Act: -0.0000

Data Index: 1873463 (The Pile)

Max Activating Token Index: 710