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

Dataset: The Pile

Neuron 4874 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: 0.6052. Min Range: -0.6052

Max Act: 0.6052. Min Act: -0.0000

Data Index: 953840 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1587645 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5242. Min Act: -0.0000

Data Index: 603629 (The Pile)

Max Activating Token Index: 367

Text #3

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.6013. Min Act: -0.0000

Data Index: 262075 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5248. Min Act: -0.0000

Data Index: 331735 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1793189 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1559325 (The Pile)

Max Activating Token Index: 739

Text #7

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1808156 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1788527 (The Pile)

Max Activating Token Index: 622

Text #9

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1867372 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4207. Min Act: -0.0000

Data Index: 490825 (The Pile)

Max Activating Token Index: 849

Text #11

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5784. Min Act: -0.0000

Data Index: 777106 (The Pile)

Max Activating Token Index: 826

Text #12

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4743. Min Act: -0.0000

Data Index: 337823 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4525. Min Act: -0.0000

Data Index: 567374 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4140. Min Act: -0.0000

Data Index: 1017962 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1256354 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1188613 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4697. Min Act: -0.0000

Data Index: 892397 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4856. Min Act: -0.0000

Data Index: 388506 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4067. Min Act: -0.0000

Data Index: 258231 (The Pile)

Max Activating Token Index: 427