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

Dataset: The Pile

Neuron 3507 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.1547. Min Act: -0.0000

Data Index: 194369 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1504301 (The Pile)

Max Activating Token Index: 966

Text #2

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0119. Min Act: -0.0000

Data Index: 602671 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 1.1547. Min Range: -1.1547

Max Act: 1.0247. Min Act: -0.0000

Data Index: 509597 (The Pile)

Max Activating Token Index: 217

Text #4

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1793614 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1122558 (The Pile)

Max Activating Token Index: 897

Text #6

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1134883 (The Pile)

Max Activating Token Index: 891

Text #7

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9577. Min Act: -0.0000

Data Index: 271118 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1404444 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1809832 (The Pile)

Max Activating Token Index: 463

Text #10

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9962. Min Act: -0.0000

Data Index: 23175 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9271. Min Act: -0.0000

Data Index: 1977044 (The Pile)

Max Activating Token Index: 332

Text #12

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1808447 (The Pile)

Max Activating Token Index: 18

Text #13

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.9237. Min Act: -0.0000

Data Index: 551116 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8861. Min Act: -0.0000

Data Index: 1096996 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8788. Min Act: -0.0000

Data Index: 1410939 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8944. Min Act: -0.0000

Data Index: 729711 (The Pile)

Max Activating Token Index: 649

Text #17

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1569306 (The Pile)

Max Activating Token Index: 1016

Text #18

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1363000 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 1.1547. Min Range: -1.1547

Max Act: 0.8915. Min Act: -0.0000

Data Index: 82332 (The Pile)

Max Activating Token Index: 167