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

Dataset: The Pile

Neuron 1544 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: 0.6972. Min Range: -0.6972

Max Act: 0.6972. Min Act: -0.0000

Data Index: 584467 (The Pile)

Max Activating Token Index: 620

Text #1

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1692037 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1225439 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5473. Min Act: -0.0000

Data Index: 198359 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1194619 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6138. Min Act: -0.0000

Data Index: 786702 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5788. Min Act: -0.0000

Data Index: 691276 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5626. Min Act: -0.0000

Data Index: 417559 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1013250 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1296076 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1052708 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1144962 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1367983 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1187799 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1108286 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5434. Min Act: -0.0000

Data Index: 795245 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1911506 (The Pile)

Max Activating Token Index: 655

Text #17

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1915946 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1506314 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1638247 (The Pile)

Max Activating Token Index: 322