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

Dataset: The Pile

Neuron 1427 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1587. Min Range: -1.1587

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1446715 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 1.1587. Min Range: -1.1587

Max Act: 1.1215. Min Act: -0.0000

Data Index: 1874749 (The Pile)

Max Activating Token Index: 256

Text #2

Max Range: 1.1587. Min Range: -1.1587

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1245818 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.1587. Min Range: -1.1587

Max Act: 1.0531. Min Act: -0.0000

Data Index: 527691 (The Pile)

Max Activating Token Index: 301

Text #4

Max Range: 1.1587. Min Range: -1.1587

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1015985 (The Pile)

Max Activating Token Index: 501

Text #5

Max Range: 1.1587. Min Range: -1.1587

Max Act: 1.0227. Min Act: -0.0000

Data Index: 475381 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 1.1587. Min Range: -1.1587

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1938254 (The Pile)

Max Activating Token Index: 111

Text #7

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.9797. Min Act: -0.0000

Data Index: 1789713 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1067450 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.9875. Min Act: -0.0000

Data Index: 403834 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.9426. Min Act: -0.0000

Data Index: 342375 (The Pile)

Max Activating Token Index: 416

Text #11

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.9345. Min Act: -0.0000

Data Index: 844571 (The Pile)

Max Activating Token Index: 467

Text #12

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1079687 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.9013. Min Act: -0.0000

Data Index: 580099 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.8728. Min Act: -0.0000

Data Index: 566267 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.8452. Min Act: -0.0000

Data Index: 1256950 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.8686. Min Act: -0.0000

Data Index: 715113 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.8664. Min Act: -0.0000

Data Index: 797753 (The Pile)

Max Activating Token Index: 233

Text #18

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1576376 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 1.1587. Min Range: -1.1587

Max Act: 0.8133. Min Act: -0.0000

Data Index: 804026 (The Pile)

Max Activating Token Index: 947