Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2727 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4917. Min Act: -0.0001

Data Index: 1304039 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4802. Min Act: -0.0001

Data Index: 1535211 (Python Code)

Max Activating Token Index: 373

Text #2

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4893. Min Act: -0.0001

Data Index: 1440106 (Python Code)

Max Activating Token Index: 976

Text #3

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4661. Min Act: -0.0001

Data Index: 156009 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4778. Min Act: -0.0001

Data Index: 1645909 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4620. Min Act: -0.0001

Data Index: 1117471 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4264. Min Act: -0.0001

Data Index: 1643353 (Python Code)

Max Activating Token Index: 365

Text #7

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4692. Min Act: -0.0001

Data Index: 1540423 (Python Code)

Max Activating Token Index: 203

Text #8

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1405669 (Python Code)

Max Activating Token Index: 739

Text #9

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4606. Min Act: -0.0001

Data Index: 1517172 (Python Code)

Max Activating Token Index: 807

Text #10

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4184. Min Act: -0.0001

Data Index: 1535824 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4138. Min Act: -0.0001

Data Index: 1599315 (Python Code)

Max Activating Token Index: 457

Text #12

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1396285 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4243. Min Act: -0.0001

Data Index: 1430153 (Python Code)

Max Activating Token Index: 323

Text #14

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4673. Min Act: -0.0001

Data Index: 1528401 (Python Code)

Max Activating Token Index: 740

Text #15

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4168. Min Act: -0.0001

Data Index: 1619454 (Python Code)

Max Activating Token Index: 229

Text #16

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4022. Min Act: -0.0001

Data Index: 1071099 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.4358. Min Act: -0.0001

Data Index: 1572907 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1524806 (Python Code)

Max Activating Token Index: 837

Text #19

Max Range: 0.4917. Min Range: -0.4917

Max Act: 0.3933. Min Act: -0.0001

Data Index: 883265 (C4 (Web Text))

Max Activating Token Index: 712