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

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

Neuron 5071 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: 0.6778. Min Range: -0.6778

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1272725 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6418. Min Act: -0.0000

Data Index: 560618 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1276205 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6060. Min Act: -0.0000

Data Index: 184207 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6407. Min Act: -0.0000

Data Index: 536129 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5720. Min Act: -0.0000

Data Index: 816411 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6401. Min Act: -0.0000

Data Index: 583379 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6068. Min Act: -0.0000

Data Index: 105776 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6194. Min Act: -0.0000

Data Index: 823355 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5598. Min Act: -0.0000

Data Index: 280682 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6187. Min Act: -0.0000

Data Index: 544674 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6311. Min Act: -0.0000

Data Index: 205680 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5424. Min Act: -0.0000

Data Index: 465582 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1103572 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5559. Min Act: -0.0000

Data Index: 637422 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5208. Min Act: -0.0000

Data Index: 400484 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5541. Min Act: -0.0000

Data Index: 621853 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5704. Min Act: -0.0000

Data Index: 853150 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1222280 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 0.6778. Min Range: -0.6778

Max Act: 0.5669. Min Act: -0.0000

Data Index: 152548 (C4 (Web Text))

Max Activating Token Index: 773