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

Dataset: The Pile

Neuron 1386 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1843591 (The Pile)

Max Activating Token Index: 813

Text #1

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7486. Min Act: 0.0000

Data Index: 1405835 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6920. Min Act: -0.0000

Data Index: 228837 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7362. Min Act: -0.0000

Data Index: 317706 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6705. Min Act: -0.0000

Data Index: 440150 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1180432 (The Pile)

Max Activating Token Index: 225

Text #6

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1180165 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5956. Min Act: -0.0000

Data Index: 142419 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1005581 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6712. Min Act: -0.0000

Data Index: 1214775 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1266928 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5707. Min Act: -0.0000

Data Index: 534166 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1207647 (The Pile)

Max Activating Token Index: 572

Text #13

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6033. Min Act: -0.0000

Data Index: 853250 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6407. Min Act: -0.0000

Data Index: 642289 (The Pile)

Max Activating Token Index: 77

Text #15

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6379. Min Act: -0.0000

Data Index: 768289 (The Pile)

Max Activating Token Index: 1016

Text #16

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6141. Min Act: -0.0000

Data Index: 923032 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6198. Min Act: -0.0000

Data Index: 17845 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6330. Min Act: -0.0000

Data Index: 950894 (The Pile)

Max Activating Token Index: 370

Text #19

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1687078 (The Pile)

Max Activating Token Index: 161