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

Dataset: The Pile

Neuron 1983 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1426520 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8131. Min Act: -0.0000

Data Index: 611247 (The Pile)

Max Activating Token Index: 443

Text #2

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.9753. Min Act: -0.0000

Data Index: 125011 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1180178 (The Pile)

Max Activating Token Index: 990

Text #4

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.8521. Min Act: -0.0000

Data Index: 628808 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1154221 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1315663 (The Pile)

Max Activating Token Index: 643

Text #7

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7617. Min Act: -0.0000

Data Index: 78012 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7702. Min Act: -0.0000

Data Index: 662595 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7762. Min Act: -0.0000

Data Index: 825673 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7108. Min Act: -0.0000

Data Index: 309839 (The Pile)

Max Activating Token Index: 487

Text #11

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1373605 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.6228. Min Act: -0.0000

Data Index: 745183 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.6083. Min Act: -0.0000

Data Index: 121608 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1479834 (The Pile)

Max Activating Token Index: 436

Text #15

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1160379 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.6014. Min Act: -0.0000

Data Index: 721653 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1070366 (The Pile)

Max Activating Token Index: 934

Text #18

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1144750 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 0.9753. Min Range: -0.9753

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1596144 (The Pile)

Max Activating Token Index: 866