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

Dataset: The Pile

Neuron 4046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4144. Min Range: -1.4144

Max Act: 1.4144. Min Act: -0.0000

Data Index: 46870 (The Pile)

Max Activating Token Index: 563

Text #1

Max Range: 1.4144. Min Range: -1.4144

Max Act: 1.0714. Min Act: -0.0000

Data Index: 167531 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 1.4144. Min Range: -1.4144

Max Act: 1.0755. Min Act: -0.0000

Data Index: 169957 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 1.4144. Min Range: -1.4144

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1560227 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.9408. Min Act: -0.0000

Data Index: 603653 (The Pile)

Max Activating Token Index: 883

Text #5

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.9490. Min Act: -0.0000

Data Index: 154497 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1684215 (The Pile)

Max Activating Token Index: 526

Text #7

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1524265 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.9246. Min Act: -0.0000

Data Index: 1798835 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1662501 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1156782 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8826. Min Act: -0.0000

Data Index: 1412506 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1738927 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1597171 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8768. Min Act: -0.0000

Data Index: 521676 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8513. Min Act: -0.0000

Data Index: 1497841 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1957082 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8761. Min Act: -0.0000

Data Index: 375211 (The Pile)

Max Activating Token Index: 452

Text #18

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1873408 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 1.4144. Min Range: -1.4144

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1827082 (The Pile)

Max Activating Token Index: 966