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

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

Neuron 1985 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0375. Min Range: -1.0375

Max Act: 1.0375. Min Act: -0.0000

Data Index: 973011 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.9323. Min Act: -0.0000

Data Index: 983103 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8772. Min Act: 0.0001

Data Index: 797099 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.8193. Min Act: -0.0000

Data Index: 240988 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7588. Min Act: -0.0000

Data Index: 917079 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7702. Min Act: -0.0000

Data Index: 224818 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6929. Min Act: -0.0000

Data Index: 674487 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7130. Min Act: -0.0000

Data Index: 984199 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7122. Min Act: -0.0000

Data Index: 320731 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6858. Min Act: -0.0000

Data Index: 804275 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6954. Min Act: -0.0000

Data Index: 670332 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6901. Min Act: -0.0000

Data Index: 526979 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.7124. Min Act: -0.0000

Data Index: 179606 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6888. Min Act: 0.0000

Data Index: 554042 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6865. Min Act: -0.0000

Data Index: 1033487 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6681. Min Act: -0.0000

Data Index: 210588 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6913. Min Act: -0.0000

Data Index: 355716 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6675. Min Act: -0.0000

Data Index: 578217 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6569. Min Act: -0.0000

Data Index: 457181 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 1.0375. Min Range: -1.0375

Max Act: 0.6523. Min Act: 0.0000

Data Index: 43311 (C4 (Web Text))

Max Activating Token Index: 54