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

Dataset: The Pile

Neuron 2192 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: 4.1950. Min Range: -4.1950

Max Act: 4.1950. Min Act: -0.0000

Data Index: 169177 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 4.1950. Min Range: -4.1950

Max Act: 4.0696. Min Act: -0.0000

Data Index: 1116131 (The Pile)

Max Activating Token Index: 512

Text #2

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.8572. Min Act: -0.0000

Data Index: 1905352 (The Pile)

Max Activating Token Index: 838

Text #3

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.5724. Min Act: -0.0000

Data Index: 616668 (The Pile)

Max Activating Token Index: 522

Text #4

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.7425. Min Act: -0.0000

Data Index: 738616 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.3671. Min Act: -0.0000

Data Index: 1764863 (The Pile)

Max Activating Token Index: 16

Text #6

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.3999. Min Act: -0.0000

Data Index: 738894 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.2582. Min Act: -0.0000

Data Index: 1715977 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.1888. Min Act: -0.0000

Data Index: 384931 (The Pile)

Max Activating Token Index: 125

Text #9

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.9576. Min Act: -0.0000

Data Index: 1526625 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.2517. Min Act: -0.0000

Data Index: 1538680 (The Pile)

Max Activating Token Index: 983

Text #11

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.9387. Min Act: -0.0000

Data Index: 1277393 (The Pile)

Max Activating Token Index: 823

Text #12

Max Range: 4.1950. Min Range: -4.1950

Max Act: 3.0235. Min Act: -0.0000

Data Index: 985541 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.8171. Min Act: -0.0000

Data Index: 786282 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.6983. Min Act: -0.0000

Data Index: 1122773 (The Pile)

Max Activating Token Index: 949

Text #15

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.9874. Min Act: -0.0000

Data Index: 1808277 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.8997. Min Act: -0.0000

Data Index: 1256398 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.8889. Min Act: -0.0000

Data Index: 116082 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.2064. Min Act: -0.0000

Data Index: 558348 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 4.1950. Min Range: -4.1950

Max Act: 2.7131. Min Act: -0.0000

Data Index: 941753 (The Pile)

Max Activating Token Index: 921