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

Dataset: The Pile

Neuron 1737 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0139. Min Range: -1.0139

Max Act: 1.0139. Min Act: -0.0000

Data Index: 1443811 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 1.0139. Min Range: -1.0139

Max Act: 1.0116. Min Act: -0.0000

Data Index: 285536 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1236393 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9364. Min Act: -0.0000

Data Index: 982838 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9837. Min Act: -0.0000

Data Index: 185175 (The Pile)

Max Activating Token Index: 484

Text #5

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9452. Min Act: -0.0000

Data Index: 204244 (The Pile)

Max Activating Token Index: 285

Text #6

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1173144 (The Pile)

Max Activating Token Index: 19

Text #7

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9497. Min Act: -0.0000

Data Index: 911284 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1145251 (The Pile)

Max Activating Token Index: 405

Text #9

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9195. Min Act: -0.0000

Data Index: 1730338 (The Pile)

Max Activating Token Index: 355

Text #10

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1307557 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8913. Min Act: -0.0000

Data Index: 805251 (The Pile)

Max Activating Token Index: 912

Text #12

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9376. Min Act: -0.0000

Data Index: 169860 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1867193 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.9319. Min Act: -0.0000

Data Index: 748425 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8989. Min Act: -0.0000

Data Index: 875680 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8961. Min Act: -0.0000

Data Index: 832094 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8676. Min Act: -0.0000

Data Index: 1960066 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1364681 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 1.0139. Min Range: -1.0139

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1139322 (The Pile)

Max Activating Token Index: 349