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

Dataset: The Pile

Neuron 1813 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.5067. Min Act: -0.0000

Data Index: 252727 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1161304 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3882. Min Act: 0.0000

Data Index: 1216237 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1851542 (The Pile)

Max Activating Token Index: 447

Text #4

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3018. Min Act: -0.0000

Data Index: 975354 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3032. Min Act: -0.0000

Data Index: 759475 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2906. Min Act: -0.0000

Data Index: 223897 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2843. Min Act: -0.0000

Data Index: 535650 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2853. Min Act: 0.0000

Data Index: 1161854 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2496. Min Act: -0.0000

Data Index: 117114 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1051973 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2606. Min Act: 0.0000

Data Index: 1620124 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1543878 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2333. Min Act: -0.0000

Data Index: 57622 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2582. Min Act: 0.0001

Data Index: 1969851 (The Pile)

Max Activating Token Index: 964

Text #15

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2424. Min Act: -0.0000

Data Index: 871505 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2482. Min Act: 0.0000

Data Index: 620636 (The Pile)

Max Activating Token Index: 232

Text #17

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1059899 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2284. Min Act: 0.0001

Data Index: 1907757 (The Pile)

Max Activating Token Index: 801

Text #19

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2375. Min Act: 0.0000

Data Index: 1586263 (The Pile)

Max Activating Token Index: 487