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

Dataset: The Pile

Neuron 1086 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1977339 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7538. Min Act: -0.0000

Data Index: 211693 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8690. Min Act: -0.0000

Data Index: 560386 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.8706. Min Act: -0.0000

Data Index: 1758254 (The Pile)

Max Activating Token Index: 367

Text #4

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1812474 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7548. Min Act: -0.0000

Data Index: 782306 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1306528 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1388055 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1129372 (The Pile)

Max Activating Token Index: 250

Text #9

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1797770 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7031. Min Act: -0.0000

Data Index: 281314 (The Pile)

Max Activating Token Index: 235

Text #11

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1491214 (The Pile)

Max Activating Token Index: 715

Text #12

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1446273 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1178549 (The Pile)

Max Activating Token Index: 16

Text #14

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7675. Min Act: -0.0000

Data Index: 358013 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1616406 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6338. Min Act: -0.0000

Data Index: 380483 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1834707 (The Pile)

Max Activating Token Index: 307

Text #18

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1889424 (The Pile)

Max Activating Token Index: 7

Text #19

Max Range: 0.9710. Min Range: -0.9710

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1580325 (The Pile)

Max Activating Token Index: 808