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

Dataset: The Pile

Neuron 2278 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: 1.4024. Min Range: -1.4024

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1784842 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1622380 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2721. Min Act: -0.0000

Data Index: 651876 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1075369 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2429. Min Act: -0.0000

Data Index: 1986595 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1274. Min Act: -0.0000

Data Index: 362508 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2184. Min Act: -0.0000

Data Index: 713639 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2017. Min Act: -0.0000

Data Index: 911121 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1514876 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1805. Min Act: -0.0000

Data Index: 650964 (The Pile)

Max Activating Token Index: 811

Text #10

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.2100. Min Act: -0.0000

Data Index: 157422 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1136230 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1746. Min Act: -0.0000

Data Index: 790608 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0935. Min Act: -0.0000

Data Index: 1822649 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0164. Min Act: -0.0000

Data Index: 864829 (The Pile)

Max Activating Token Index: 298

Text #15

Max Range: 1.4024. Min Range: -1.4024

Max Act: 0.8798. Min Act: -0.0000

Data Index: 1170493 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 1.4024. Min Range: -1.4024

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1366311 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 1.4024. Min Range: -1.4024

Max Act: 0.6972. Min Act: -0.0000

Data Index: 951439 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 1.4024. Min Range: -1.4024

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1564447 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 1.4024. Min Range: -1.4024

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1984804 (The Pile)

Max Activating Token Index: 686