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

Dataset: The Pile

Neuron 1878 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: 1.3598. Min Range: -1.3598

Max Act: 1.3598. Min Act: -0.0000

Data Index: 377668 (The Pile)

Max Activating Token Index: 672

Text #1

Max Range: 1.3598. Min Range: -1.3598

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1088385 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 1.3598. Min Range: -1.3598

Max Act: 1.0590. Min Act: -0.0000

Data Index: 853654 (The Pile)

Max Activating Token Index: 373

Text #3

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9811. Min Act: -0.0000

Data Index: 1041128 (The Pile)

Max Activating Token Index: 363

Text #4

Max Range: 1.3598. Min Range: -1.3598

Max Act: 1.0071. Min Act: -0.0000

Data Index: 813423 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9503. Min Act: -0.0000

Data Index: 252282 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1221372 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1593515 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1677586 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9022. Min Act: -0.0000

Data Index: 247790 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.8673. Min Act: -0.0000

Data Index: 100998 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9128. Min Act: -0.0000

Data Index: 327378 (The Pile)

Max Activating Token Index: 778

Text #12

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.8825. Min Act: -0.0000

Data Index: 522066 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9279. Min Act: -0.0000

Data Index: 755847 (The Pile)

Max Activating Token Index: 604

Text #14

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1079224 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.9202. Min Act: -0.0000

Data Index: 223743 (The Pile)

Max Activating Token Index: 223

Text #16

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.8568. Min Act: -0.0000

Data Index: 5116 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.8498. Min Act: -0.0000

Data Index: 169081 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1074101 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 1.3598. Min Range: -1.3598

Max Act: 0.8848. Min Act: -0.0000

Data Index: 968385 (The Pile)

Max Activating Token Index: 726