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

Dataset: The Pile

Neuron 3290 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.3330. Min Range: -11.3330

Max Act: 11.3330. Min Act: -0.0000

Data Index: 1565886 (The Pile)

Max Activating Token Index: 505

Text #1

Max Range: 11.3330. Min Range: -11.3330

Max Act: 10.7971. Min Act: -0.0000

Data Index: 1401235 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 11.3330. Min Range: -11.3330

Max Act: 10.0227. Min Act: -0.0000

Data Index: 1476154 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 11.3330. Min Range: -11.3330

Max Act: 9.8544. Min Act: -0.0000

Data Index: 964314 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 11.3330. Min Range: -11.3330

Max Act: 10.1777. Min Act: -0.0000

Data Index: 452388 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 11.3330. Min Range: -11.3330

Max Act: 9.1885. Min Act: -0.0000

Data Index: 1680931 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 11.3330. Min Range: -11.3330

Max Act: 8.9689. Min Act: -0.0000

Data Index: 1812388 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 11.3330. Min Range: -11.3330

Max Act: 9.3976. Min Act: -0.0000

Data Index: 914714 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 11.3330. Min Range: -11.3330

Max Act: 8.7201. Min Act: -0.0000

Data Index: 1375939 (The Pile)

Max Activating Token Index: 543

Text #9

Max Range: 11.3330. Min Range: -11.3330

Max Act: 8.7145. Min Act: -0.0000

Data Index: 1185964 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 11.3330. Min Range: -11.3330

Max Act: 8.9487. Min Act: -0.0000

Data Index: 298159 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 11.3330. Min Range: -11.3330

Max Act: 8.6531. Min Act: -0.0000

Data Index: 1918572 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 11.3330. Min Range: -11.3330

Max Act: 8.3113. Min Act: -0.0000

Data Index: 1522940 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 11.3330. Min Range: -11.3330

Max Act: 8.4785. Min Act: -0.0000

Data Index: 1672101 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 11.3330. Min Range: -11.3330

Max Act: 7.6719. Min Act: -0.0000

Data Index: 963231 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 11.3330. Min Range: -11.3330

Max Act: 7.7496. Min Act: -0.0000

Data Index: 394413 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 11.3330. Min Range: -11.3330

Max Act: 7.5079. Min Act: -0.0000

Data Index: 799091 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 11.3330. Min Range: -11.3330

Max Act: 7.6939. Min Act: -0.0000

Data Index: 1143838 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 11.3330. Min Range: -11.3330

Max Act: 7.6397. Min Act: -0.0000

Data Index: 1303399 (The Pile)

Max Activating Token Index: 339

Text #19

Max Range: 11.3330. Min Range: -11.3330

Max Act: 7.0877. Min Act: -0.0000

Data Index: 663923 (The Pile)

Max Activating Token Index: 847