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

Dataset: The Pile

Neuron 3355 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: 0.1106. Min Range: -0.1106

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1994828 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1589240 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.1000. Min Act: -0.0000

Data Index: 601737 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0913. Min Act: -0.0000

Data Index: 791357 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1803846 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1720807 (The Pile)

Max Activating Token Index: 614

Text #6

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0808. Min Act: -0.0000

Data Index: 293333 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1381264 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1612722 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0662. Min Act: -0.0000

Data Index: 357958 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1054810 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0739. Min Act: -0.0000

Data Index: 501876 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0677. Min Act: -0.0000

Data Index: 654200 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1620155 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0780. Min Act: -0.0000

Data Index: 484097 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0718. Min Act: -0.0000

Data Index: 250678 (The Pile)

Max Activating Token Index: 348

Text #16

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1632582 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0604. Min Act: -0.0000

Data Index: 377470 (The Pile)

Max Activating Token Index: 769

Text #18

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0531. Min Act: -0.0000

Data Index: 1919980 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 0.1106. Min Range: -0.1106

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1720219 (The Pile)

Max Activating Token Index: 619