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

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

Neuron 626 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.8158. Min Act: -0.0001

Data Index: 136874 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7348. Min Act: -0.0000

Data Index: 184798 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7421. Min Act: -0.0000

Data Index: 597147 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6470. Min Act: -0.0001

Data Index: 1287485 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6719. Min Act: -0.0000

Data Index: 818197 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6656. Min Act: -0.0001

Data Index: 1047793 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6613. Min Act: -0.0001

Data Index: 656319 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6837. Min Act: -0.0000

Data Index: 759398 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6880. Min Act: -0.0000

Data Index: 934146 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.5968. Min Act: -0.0000

Data Index: 592486 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1184391 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6504. Min Act: -0.0001

Data Index: 673585 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6702. Min Act: -0.0000

Data Index: 1238248 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6077. Min Act: -0.0000

Data Index: 547596 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1069597 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6173. Min Act: -0.0000

Data Index: 884235 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6358. Min Act: -0.0000

Data Index: 215884 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6490. Min Act: -0.0000

Data Index: 873257 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6121. Min Act: -0.0000

Data Index: 708315 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.8158. Min Range: -0.8158

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1267972 (C4 (Web Text))

Max Activating Token Index: 936