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

Dataset: The Pile

Neuron 2566 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: 1.2252. Min Range: -1.2252

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1550460 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.1501. Min Act: -0.0000

Data Index: 746686 (The Pile)

Max Activating Token Index: 642

Text #2

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1188327 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.9508. Min Act: -0.0000

Data Index: 764648 (The Pile)

Max Activating Token Index: 942

Text #4

Max Range: 1.2252. Min Range: -1.2252

Max Act: 1.0126. Min Act: -0.0000

Data Index: 759129 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.9839. Min Act: -0.0000

Data Index: 1169665 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.9176. Min Act: -0.0000

Data Index: 45267 (The Pile)

Max Activating Token Index: 200

Text #7

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1746933 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8885. Min Act: -0.0000

Data Index: 928262 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1141689 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8775. Min Act: 0.0000

Data Index: 234151 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1861273 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1090860 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1720153 (The Pile)

Max Activating Token Index: 677

Text #14

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8167. Min Act: -0.0000

Data Index: 318122 (The Pile)

Max Activating Token Index: 875

Text #15

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1598808 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8378. Min Act: -0.0000

Data Index: 548293 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8965. Min Act: 0.0000

Data Index: 112012 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.7971. Min Act: -0.0000

Data Index: 1510527 (The Pile)

Max Activating Token Index: 41

Text #19

Max Range: 1.2252. Min Range: -1.2252

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1610824 (The Pile)

Max Activating Token Index: 854