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

Dataset: The Pile

Neuron 3227 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1284706 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9233. Min Act: -0.0000

Data Index: 497512 (The Pile)

Max Activating Token Index: 126

Text #2

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.9061. Min Act: -0.0000

Data Index: 605755 (The Pile)

Max Activating Token Index: 831

Text #3

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1903872 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8131. Min Act: -0.0000

Data Index: 1884174 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8500. Min Act: -0.0000

Data Index: 476322 (The Pile)

Max Activating Token Index: 638

Text #6

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8361. Min Act: -0.0000

Data Index: 14851 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1318841 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1020033 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1005847 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1810132 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7688. Min Act: -0.0000

Data Index: 415850 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7742. Min Act: -0.0000

Data Index: 558876 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6883. Min Act: -0.0000

Data Index: 272218 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1181241 (The Pile)

Max Activating Token Index: 483

Text #15

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7744. Min Act: -0.0000

Data Index: 280639 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6839. Min Act: -0.0000

Data Index: 1211721 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7548. Min Act: -0.0000

Data Index: 1712342 (The Pile)

Max Activating Token Index: 682

Text #18

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7028. Min Act: -0.0000

Data Index: 330392 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1283545 (The Pile)

Max Activating Token Index: 1018