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

Dataset: The Pile

Neuron 2834 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: 0.7120. Min Range: -0.7120

Max Act: 0.7120. Min Act: -0.0000

Data Index: 747886 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1721352 (The Pile)

Max Activating Token Index: 134

Text #2

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6866. Min Act: -0.0000

Data Index: 1608097 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1192760 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1822736 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6612. Min Act: -0.0000

Data Index: 462239 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6507. Min Act: -0.0000

Data Index: 874835 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6963. Min Act: 0.0000

Data Index: 1348334 (The Pile)

Max Activating Token Index: 985

Text #8

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1833860 (The Pile)

Max Activating Token Index: 67

Text #9

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1189966 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5974. Min Act: -0.0000

Data Index: 1179874 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1020144 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1530121 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1729540 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1296169 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1896526 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1034665 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5801. Min Act: -0.0000

Data Index: 94374 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5410. Min Act: -0.0000

Data Index: 732456 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 0.7120. Min Range: -0.7120

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1131952 (The Pile)

Max Activating Token Index: 221