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

Dataset: The Pile

Neuron 499 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: 0.6551. Min Range: -0.6551

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1625358 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5971. Min Act: -0.0000

Data Index: 500379 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1614202 (The Pile)

Max Activating Token Index: 225

Text #3

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5637. Min Act: -0.0000

Data Index: 792919 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1895654 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5203. Min Act: -0.0000

Data Index: 1387725 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5978. Min Act: -0.0000

Data Index: 135930 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1121742 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5054. Min Act: -0.0000

Data Index: 608727 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1365598 (The Pile)

Max Activating Token Index: 847

Text #10

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.3555. Min Act: -0.0000

Data Index: 370121 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4892. Min Act: -0.0000

Data Index: 309823 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1920239 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1495118 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1476711 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4929. Min Act: -0.0000

Data Index: 483840 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5188. Min Act: -0.0000

Data Index: 1794590 (The Pile)

Max Activating Token Index: 330

Text #17

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.3920. Min Act: -0.0000

Data Index: 388264 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1733098 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4666. Min Act: -0.0000

Data Index: 889651 (The Pile)

Max Activating Token Index: 341