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

Dataset: The Pile

Neuron 3625 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.3087. Min Act: -0.0000

Data Index: 1320442 (The Pile)

Max Activating Token Index: 494

Text #1

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.0583. Min Act: -0.0000

Data Index: 1897792 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.0068. Min Act: -0.0000

Data Index: 1021245 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.5999. Min Act: -0.0000

Data Index: 169487 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.1196. Min Act: -0.0000

Data Index: 1180159 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.8542. Min Act: -0.0000

Data Index: 933463 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.2976. Min Act: -0.0000

Data Index: 390306 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.6966. Min Act: -0.0000

Data Index: 506109 (The Pile)

Max Activating Token Index: 913

Text #8

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.4596. Min Act: -0.0000

Data Index: 1198092 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.2288. Min Act: -0.0000

Data Index: 1386968 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.1945. Min Act: -0.0000

Data Index: 593888 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.5748. Min Act: -0.0000

Data Index: 486360 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.2405. Min Act: -0.0000

Data Index: 901598 (The Pile)

Max Activating Token Index: 100

Text #13

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.0950. Min Act: -0.0000

Data Index: 1168349 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 3.3087. Min Range: -3.3087

Max Act: 1.9573. Min Act: -0.0000

Data Index: 990737 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 3.3087. Min Range: -3.3087

Max Act: 1.9709. Min Act: -0.0000

Data Index: 989006 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.1844. Min Act: -0.0000

Data Index: 952027 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 3.3087. Min Range: -3.3087

Max Act: 1.8736. Min Act: -0.0000

Data Index: 562274 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 3.3087. Min Range: -3.3087

Max Act: 2.0386. Min Act: -0.0000

Data Index: 197090 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 3.3087. Min Range: -3.3087

Max Act: 1.8024. Min Act: -0.0000

Data Index: 938475 (The Pile)

Max Activating Token Index: 209