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

Dataset: The Pile

Neuron 1913 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: 1.2336. Min Range: -1.2336

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1525491 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.2336. Min Range: -1.2336

Max Act: 1.2336. Min Act: -0.0000

Data Index: 960386 (The Pile)

Max Activating Token Index: 479

Text #2

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1645051 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1964903 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1400393 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9769. Min Act: -0.0000

Data Index: 488776 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.7656. Min Act: -0.0000

Data Index: 17937 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8699. Min Act: -0.0000

Data Index: 78885 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8865. Min Act: -0.0000

Data Index: 1534045 (The Pile)

Max Activating Token Index: 368

Text #9

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1081874 (The Pile)

Max Activating Token Index: 778

Text #10

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1580609 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1793773 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8155. Min Act: -0.0000

Data Index: 325769 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8113. Min Act: -0.0000

Data Index: 110281 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1036787 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8352. Min Act: -0.0000

Data Index: 46680 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8803. Min Act: -0.0001

Data Index: 675213 (The Pile)

Max Activating Token Index: 63

Text #17

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.7848. Min Act: -0.0000

Data Index: 667401 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.8236. Min Act: -0.0000

Data Index: 553375 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 1.2336. Min Range: -1.2336

Max Act: 0.7759. Min Act: -0.0000

Data Index: 436534 (The Pile)

Max Activating Token Index: 357