Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 5030 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.4090. Min Act: -0.0000

Data Index: 570662 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1296. Min Act: -0.0000

Data Index: 677421 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0895. Min Act: -0.0000

Data Index: 354014 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0070. Min Act: -0.0000

Data Index: 47078 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0402. Min Act: -0.0000

Data Index: 332421 (The Pile)

Max Activating Token Index: 301

Text #5

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0345. Min Act: -0.0000

Data Index: 6428 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1800751 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0949. Min Act: -0.0000

Data Index: 87813 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9360. Min Act: -0.0000

Data Index: 475789 (The Pile)

Max Activating Token Index: 999

Text #9

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1245397 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1090842 (The Pile)

Max Activating Token Index: 395

Text #11

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1157897 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0228. Min Act: -0.0000

Data Index: 114122 (The Pile)

Max Activating Token Index: 697

Text #13

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1701375 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1250900 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9348. Min Act: -0.0000

Data Index: 1605299 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1918024 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1992184 (The Pile)

Max Activating Token Index: 663

Text #18

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9127. Min Act: -0.0000

Data Index: 711081 (The Pile)

Max Activating Token Index: 114

Text #19

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1369575 (The Pile)

Max Activating Token Index: 618