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

Dataset: The Pile

Neuron 3869 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.5325. Min Act: -0.0000

Data Index: 26244 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.7113. Min Act: -0.0000

Data Index: 172098 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.2469. Min Act: -0.0000

Data Index: 573714 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.3406. Min Act: -0.0000

Data Index: 264113 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.9984. Min Act: -0.0000

Data Index: 1922078 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.0122. Min Act: -0.0000

Data Index: 1336926 (The Pile)

Max Activating Token Index: 413

Text #6

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.8250. Min Act: -0.0000

Data Index: 1453465 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.6886. Min Act: -0.0000

Data Index: 1986859 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.6371. Min Act: -0.0000

Data Index: 1124330 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.7503. Min Act: -0.0000

Data Index: 589501 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.8940. Min Act: -0.0000

Data Index: 608487 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.8829. Min Act: -0.0000

Data Index: 602933 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.7253. Min Act: -0.0000

Data Index: 1055554 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.5905. Min Act: -0.0000

Data Index: 1837375 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.7195. Min Act: -0.0000

Data Index: 1675933 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.6939. Min Act: -0.0000

Data Index: 191959 (The Pile)

Max Activating Token Index: 206

Text #16

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.6884. Min Act: -0.0000

Data Index: 1385050 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.6941. Min Act: -0.0000

Data Index: 235882 (The Pile)

Max Activating Token Index: 369

Text #18

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.6940. Min Act: -0.0000

Data Index: 1822249 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.6684. Min Act: -0.0000

Data Index: 1027372 (The Pile)

Max Activating Token Index: 368