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

Dataset: The Pile

Neuron 1928 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.3518. Min Act: -0.0000

Data Index: 1267431 (The Pile)

Max Activating Token Index: 862

Text #1

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.5280. Min Act: -0.0000

Data Index: 779757 (The Pile)

Max Activating Token Index: 911

Text #2

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1666870 (The Pile)

Max Activating Token Index: 267

Text #3

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.4606. Min Act: -0.0000

Data Index: 238600 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.3377. Min Act: -0.0000

Data Index: 1943997 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.3358. Min Act: -0.0000

Data Index: 1764686 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1230722 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2704. Min Act: -0.0000

Data Index: 1564251 (The Pile)

Max Activating Token Index: 939

Text #8

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2497. Min Act: -0.0000

Data Index: 457182 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.0968. Min Act: -0.0000

Data Index: 380919 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2432. Min Act: -0.0000

Data Index: 1156831 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2566. Min Act: -0.0000

Data Index: 313046 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1686. Min Act: -0.0000

Data Index: 42617 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1773880 (The Pile)

Max Activating Token Index: 283

Text #14

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2164. Min Act: -0.0000

Data Index: 324633 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 1.5280. Min Range: -1.5280

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1385666 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1383. Min Act: -0.0000

Data Index: 311481 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1233492 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1121. Min Act: -0.0000

Data Index: 55753 (The Pile)

Max Activating Token Index: 308

Text #19

Max Range: 1.5280. Min Range: -1.5280

Max Act: 1.1831. Min Act: -0.0000

Data Index: 737039 (The Pile)

Max Activating Token Index: 340